{"items":[{"v":1,"id":"model:hf:unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF","slug":"model-unsloth-qwen3-coder-30b-a3b-instruct-gguf","kind":"model","category":"llm","title":"Qwen3-Coder-30B-A3B-Instruct-GGUF","summary":"See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats.","source":{"provider":"hf","ref":"unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF","url":"https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF","rev":"b17cb02dd882d5b6ab62fc777ad2995f19668350","fetchedAt":"2026-10-02T21:01:21.484Z","etag":"W/\"407b-lXflMaeFHq6AI/qViaFi0CFBiC8\""},"author":{"name":"unsloth","url":"https://huggingface.co/unsloth"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","url":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE","open":true},"metrics":{"downloads":8649679,"downloadsWeek":327838,"likes":1099,"takenAt":"2026-10-02T21:01:21.484Z"},"tags":["transformers","gguf","unsloth","qwen3","qwen","text-generation","endpoints_compatible","imatrix","conversational"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2026-01-30T06:29:38.000Z","collectedAt":"2026-10-02T21:01:21.484Z","review":{"numbers":["8,649,679 downloads on Hugging Face","1,099 likes","license apache-2.0","17 GB for Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:21.484Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":506244275360,"suggestedFile":"Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf","requirements":{"ramGb":21,"diskBytes":18556689568,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:ornith-ai/Ornith-1.5-9B-GGUF","slug":"model-ornith-ai-ornith-1-5-9b-gguf","kind":"model","category":"llm","title":"Ornith-1.5-9B-GGUF","summary":"Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.","source":{"provider":"hf","ref":"ornith-ai/Ornith-1.5-9B-GGUF","url":"https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF","rev":"abdd624b12ebf020b767fff532ff44fe552b28c3","fetchedAt":"2026-10-02T21:01:24.869Z","etag":"W/\"2c5d-ypsIyur5XI/vDN2J75KL3T7bicM\""},"author":{"name":"ornith-ai","url":"https://huggingface.co/ornith-ai"},"license":{"spdx":"mit","raw":"mit","url":"https://huggingface.co/ornith-ai/Ornith-1.5-9B/blob/main/LICENSE","open":true},"metrics":{"downloads":5051736,"downloadsWeek":327838,"likes":479,"takenAt":"2026-10-02T21:01:24.869Z"},"tags":["transformers","gguf","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-08-24T02:45:24.000Z","collectedAt":"2026-10-02T21:01:24.869Z","review":{"numbers":["5,051,736 downloads on Hugging Face","479 likes","license mit","5.4 GB for Ornith-1.5-9B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:24.869Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":49096623328,"suggestedFile":"Ornith-1.5-9B-Q4_K_M.gguf","requirements":{"ramGb":7,"diskBytes":5780090816,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:prism-ml/Ternary-Bonsai-2-27B-gguf","slug":"model-prism-ml-ternary-bonsai-2-27b-gguf","kind":"model","category":"llm","title":"Ternary-Bonsai-2-27B-gguf","summary":"Prism ML Website Whitepaper Demo & Examples Discord","source":{"provider":"hf","ref":"prism-ml/Ternary-Bonsai-2-27B-gguf","url":"https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf","rev":"b072e1d3b35a0a630cece372c2127528e0994386","fetchedAt":"2026-10-02T21:01:27.529Z","etag":"W/\"3258-TbK0h+PjgNxJwTad7lUe+yTqLzE\""},"author":{"name":"prism-ml","url":"https://huggingface.co/prism-ml"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":3869715,"downloadsWeek":327838,"likes":2356,"takenAt":"2026-10-02T21:01:27.529Z"},"tags":["llama.cpp","gguf","ternary","2-bit","llama-cpp","cuda","metal","on-device","hybrid-attention","prismml","bonsai","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-09-25T21:58:06.000Z","collectedAt":"2026-10-02T21:01:27.529Z","review":{"numbers":["3,869,715 downloads on Hugging Face","2,356 likes","license apache-2.0","50 GB for Ternary-Bonsai-2-27B-F16.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:27.529Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":68521619616,"suggestedFile":"Ternary-Bonsai-2-27B-F16.gguf","requirements":{"ramGb":59,"diskBytes":53808408928,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:ornith-ai/Ornith-1.5-35B-A3B-GGUF","slug":"model-ornith-ai-ornith-1-5-35b-a3b-gguf","kind":"model","category":"llm","title":"Ornith-1.5-35B-A3B-GGUF","summary":"Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.","source":{"provider":"hf","ref":"ornith-ai/Ornith-1.5-35B-A3B-GGUF","url":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF","rev":"12393612fd4f730ff5aadc23e9b8f9648aa49ceb","fetchedAt":"2026-10-02T20:59:06.965Z","etag":"W/\"2c7b-rSKgDh2Xr28rX+3uKwjBRFEil44\""},"author":{"name":"ornith-ai","url":"https://huggingface.co/ornith-ai"},"license":{"spdx":"mit","raw":"mit","url":"https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/main/LICENSE","open":true},"metrics":{"downloads":3570548,"downloadsWeek":327838,"likes":473,"takenAt":"2026-10-02T20:59:06.965Z"},"tags":["transformers","gguf","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-08-24T03:43:47.000Z","collectedAt":"2026-10-02T20:59:06.965Z","review":{"numbers":["3,570,548 downloads on Hugging Face","473 likes","license mit","20 GB for Ornith-1.5-35B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:06.965Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":186041692896,"suggestedFile":"Ornith-1.5-35B-Q4_K_M.gguf","requirements":{"ramGb":24,"diskBytes":21713463040,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:ornith-ai/Ornith-1.0-9B-GGUF","slug":"model-ornith-ai-ornith-1-0-9b-gguf","kind":"model","category":"llm","title":"Ornith-1.0-9B-GGUF","summary":"Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.","source":{"provider":"hf","ref":"ornith-ai/Ornith-1.0-9B-GGUF","url":"https://huggingface.co/ornith-ai/Ornith-1.0-9B-GGUF","rev":"3296bc7a404871a72ac3f1903f561459c09b5c17","fetchedAt":"2026-10-02T20:59:09.659Z","etag":"W/\"2ab1-/4RyOHQlvvxLIKug0UQ8mTwG2Dk\""},"author":{"name":"ornith-ai","url":"https://huggingface.co/ornith-ai"},"license":{"spdx":"mit","raw":"mit","url":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B-GGUF/blob/main/LICENSE","open":true},"metrics":{"downloads":2570756,"downloadsWeek":327838,"likes":673,"takenAt":"2026-10-02T20:59:09.659Z"},"tags":["transformers","gguf","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-06-25T14:12:12.000Z","collectedAt":"2026-10-02T20:59:09.659Z","review":{"numbers":["2,570,756 downloads on Hugging Face","673 likes","license mit","5.2 GB for ornith-1.0-9b-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:09.659Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":46904534752,"suggestedFile":"ornith-1.0-9b-Q4_K_M.gguf","requirements":{"ramGb":7,"diskBytes":5629108704,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:CMSManhattan/JiRackUltra_1b","slug":"model-cmsmanhattan-jirackultra-1b","kind":"model","category":"llm","title":"JiRackUltra_1b","summary":"JiRack Ultra 1B (CPU) A fast and efficient ~1.5B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Tool call, and Ro…","source":{"provider":"hf","ref":"CMSManhattan/JiRackUltra_1b","url":"https://huggingface.co/CMSManhattan/JiRackUltra_1b","rev":"18cbff46548f6f7acea6dc78d997514df50a7ec2","fetchedAt":"2026-10-02T20:59:11.664Z","etag":"W/\"2975-stbGUrdjqnhtp7fJZK7N/+OmnyU\""},"author":{"name":"CMSManhattan","url":"https://huggingface.co/CMSManhattan"},"license":{"spdx":"mit","raw":"mit","open":true},"metrics":{"downloads":2532192,"downloadsWeek":327838,"likes":0,"takenAt":"2026-10-02T20:59:11.664Z"},"tags":["safetensors","gguf","qwen2","text-generation","ternary","bitnet","1.58bit","cpu","qwen2.5","deepseek","efficient","low-memory","jirack","web-ui","routing","tool-call","robotics","conversational","en","zh","ja","ko","fr","es","pt","de","it","ru","ar","vi","th","endpoints_compatible"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-10-01T18:10:57.000Z","collectedAt":"2026-10-02T20:59:11.664Z","review":{"numbers":["2,532,192 downloads on Hugging Face","0 likes","license mit","1.0 GB for JiRackUltra_1b_Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:11.664Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":16069462008,"suggestedFile":"JiRackUltra_1b_Q4_K_M.gguf","requirements":{"ramGb":2,"diskBytes":1117320608,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:mixedbread-ai/mxbai-embed-large-v1","slug":"model-mixedbread-ai-mxbai-embed-large-v1","kind":"model","category":"embedding","title":"mxbai-embed-large-v1","summary":"embedding model by mixedbread-ai, gguf files on Hugging Face.","source":{"provider":"hf","ref":"mixedbread-ai/mxbai-embed-large-v1","url":"https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1","rev":"b33106f585b9ce46904ad7443a3b52b7a63e231c","fetchedAt":"2026-10-02T21:01:20.425Z","etag":"W/\"24e9c-OnKo1Lmmyzx1Xa0xGXUbHiZCmHg\""},"author":{"name":"mixedbread-ai","url":"https://huggingface.co/mixedbread-ai"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":1983334,"downloadsWeek":4402710,"likes":826,"takenAt":"2026-10-02T21:01:20.425Z"},"tags":["sentence-transformers","onnx","safetensors","openvino","gguf","bert","feature-extraction","mteb","transformers.js","transformers","en","model-index","text-embeddings-inference","endpoints_compatible"],"pipeline":"feature-extraction","links":{"github":"mixedbread-ai/batched","npm":"@huggingface/transformers"},"updatedAt":"2026-01-23T11:59:58.000Z","collectedAt":"2026-10-02T21:01:20.425Z","review":{"numbers":["1,983,334 downloads on Hugging Face","826 likes","license apache-2.0","0.6 GB for gguf/mxbai-embed-large-v1-f16.gguf","4,402,710 npm downloads a week for @huggingface/transformers","latest @huggingface/transformers@4.3.0"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:20.425Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":5355731041,"suggestedFile":"gguf/mxbai-embed-large-v1-f16.gguf","requirements":{"ramGb":2,"diskBytes":669603712,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp"]}},{"v":1,"id":"model:hf:handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf","slug":"model-handy-computer-nemotron-3-5-asr-streaming-0-6b-gguf","kind":"model","category":"speech","title":"nemotron-3.5-asr-streaming-0.6b-gguf","summary":"nemotron-3.5-asr-streaming-0.6b: transcribe.cpp GGUF","source":{"provider":"hf","ref":"handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf","url":"https://huggingface.co/handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf","rev":"8139c4ec14bdc45c361adf8d57c27c28e7478272","fetchedAt":"2026-10-02T21:01:19.412Z","etag":"W/\"12fc-T4XRo1z02QFd/G+yClo/40fz+Zo\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":null,"raw":"other","url":"https://openmdw.ai/license/1-1/","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":1796437,"likes":12,"takenAt":"2026-10-02T21:01:19.412Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","parakeet","conformer","rnnt","streaming","cache-aware","multilingual","automatic-speech-recognition","en","es","fr","it","pt","nl","de","tr","ru","ar","hi","ja","ko","vi","uk","pl","sv","cs","nb","da","bg","fi","hr","sk","zh","hu","ro","et"],"pipeline":"automatic-speech-recognition","links":{"github":"NVIDIA-NeMo/NeMo"},"updatedAt":"2026-09-15T07:05:40.000Z","collectedAt":"2026-10-02T21:01:19.412Z","review":{"numbers":["1,796,437 downloads on Hugging Face","12 likes","license other","0.5 GB for nemotron-3.5-asr-streaming-0.6b-Q4_K_M.gguf"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:19.412Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":6257957696,"suggestedFile":"nemotron-3.5-asr-streaming-0.6b-Q4_K_M.gguf","requirements":{"ramGb":2,"diskBytes":495831520,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"]}},{"v":1,"id":"model:hf:ornith-ai/Ornith-1.0-35B-GGUF","slug":"model-ornith-ai-ornith-1-0-35b-gguf","kind":"model","category":"llm","title":"Ornith-1.0-35B-GGUF","summary":"Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.","source":{"provider":"hf","ref":"ornith-ai/Ornith-1.0-35B-GGUF","url":"https://huggingface.co/ornith-ai/Ornith-1.0-35B-GGUF","rev":"383064f72a1ef3087b779f268d3ca117eb989aac","fetchedAt":"2026-10-02T20:59:17.156Z","etag":"W/\"2a4c-Ypb04/eL4PrNUTUrss3UkqCCOOQ\""},"author":{"name":"ornith-ai","url":"https://huggingface.co/ornith-ai"},"license":{"spdx":"mit","raw":"mit","url":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-GGUF/blob/main/LICENSE","open":true},"metrics":{"downloads":1679944,"downloadsWeek":327838,"likes":1054,"takenAt":"2026-10-02T20:59:17.156Z"},"tags":["transformers","gguf","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-07-18T03:15:03.000Z","collectedAt":"2026-10-02T20:59:17.156Z","review":{"numbers":["1,679,944 downloads on Hugging Face","1,054 likes","license mit","20 GB for ornith-1.0-35b-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:17.156Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":180689816576,"suggestedFile":"ornith-1.0-35b-Q4_K_M.gguf","requirements":{"ramGb":24,"diskBytes":21166757760,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:handy-computer/parakeet-unified-en-0.6b-gguf","slug":"model-handy-computer-parakeet-unified-en-0-6b-gguf","kind":"model","category":"speech","title":"parakeet-unified-en-0.6b-gguf","summary":"parakeet-unified-en-0.6b: transcribe.cpp GGUF","source":{"provider":"hf","ref":"handy-computer/parakeet-unified-en-0.6b-gguf","url":"https://huggingface.co/handy-computer/parakeet-unified-en-0.6b-gguf","rev":"d5249700b2382bf5c5024c2421d101b8db54a629","fetchedAt":"2026-10-02T21:01:22.409Z","etag":"W/\"c93-Fp128/gxFmJ4BTaO0coKiVBxQvA\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":"cc-by-4.0","raw":"cc-by-4.0","open":true},"metrics":{"downloads":1570880,"likes":9,"takenAt":"2026-10-02T21:01:22.409Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","parakeet","conformer","rnnt","automatic-speech-recognition","en"],"pipeline":"automatic-speech-recognition","links":{"github":"NVIDIA-NeMo/NeMo"},"updatedAt":"2026-09-15T07:05:43.000Z","collectedAt":"2026-10-02T21:01:22.409Z","review":{"numbers":["1,570,880 downloads on Hugging Face","9 likes","license cc-by-4.0","0.4 GB for parakeet-unified-en-0.6b-Q4_K_M.gguf"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:22.409Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":6064056320,"suggestedFile":"parakeet-unified-en-0.6b-Q4_K_M.gguf","requirements":{"ramGb":2,"diskBytes":477274496,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"]}},{"v":1,"id":"model:hf:antirez/deepseek-v4-gguf","slug":"model-antirez-deepseek-v4-gguf","kind":"model","category":"llm","title":"deepseek-v4-gguf","summary":"This quants are specific for the DS4 inference engine. They may work with other inference engines or not (they should, but not the MTP model which requires a specific loader).","source":{"provider":"hf","ref":"antirez/deepseek-v4-gguf","url":"https://huggingface.co/antirez/deepseek-v4-gguf","rev":"f71f23d552d664e523b422157b2befbf74040380","fetchedAt":"2026-10-02T20:59:19.804Z","etag":"W/\"34e8-1NNv4bxFM/6LLpqsCwvxVHA1n60\""},"author":{"name":"antirez","url":"https://huggingface.co/antirez"},"license":{"spdx":"mit","raw":"mit","open":true},"metrics":{"downloads":1487199,"downloadsWeek":327838,"likes":477,"takenAt":"2026-10-02T20:59:19.804Z"},"tags":["gguf","quantized","deepseek","deepseek-v4","deepseek-v4-flash","moe","mixture-of-experts","2-bit","4-bit","iq2_xxs","q2_k","q4_k","ds4","apple-silicon","metal","text-generation","en","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"deepseek-ai/DeepSeek-V3","npm":"node-llama-cpp"},"updatedAt":"2026-08-31T18:47:37.000Z","collectedAt":"2026-10-02T20:59:19.804Z","review":{"numbers":["1,487,199 downloads on Hugging Face","477 likes","license mit","3.5 GB for DeepSeek-V4-Flash-MTP-Q4K-Q8_0-F32.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:19.804Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":3761582781120,"suggestedFile":"DeepSeek-V4-Flash-MTP-Q4K-Q8_0-F32.gguf","requirements":{"ramGb":5,"diskBytes":3807602400,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:ornith-ai/Ornith-1.5-397B-GGUF","slug":"model-ornith-ai-ornith-1-5-397b-gguf","kind":"model","category":"llm","title":"Ornith-1.5-397B-GGUF","summary":"Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.","source":{"provider":"hf","ref":"ornith-ai/Ornith-1.5-397B-GGUF","url":"https://huggingface.co/ornith-ai/Ornith-1.5-397B-GGUF","rev":"771a73943cafcf88d496c423ea5dd3a1622b1c10","fetchedAt":"2026-10-02T20:59:23.628Z","etag":"W/\"2bfe-Y9CKQCGbnt8eZBiPItb257DvaXc\""},"author":{"name":"ornith-ai","url":"https://huggingface.co/ornith-ai"},"license":{"spdx":"mit","raw":"mit","url":"https://huggingface.co/ornith-ai/Ornith-1.5-397B/blob/main/LICENSE","open":true},"metrics":{"downloads":1260187,"downloadsWeek":327838,"likes":40,"takenAt":"2026-10-02T20:59:23.628Z"},"tags":["transformers","gguf","text-generation","endpoints_compatible","imatrix","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-08-24T05:54:49.000Z","collectedAt":"2026-10-02T20:59:23.628Z","review":{"numbers":["1,260,187 downloads on Hugging Face","40 likes","license mit","228 GB for Ornith-1.5-397B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:23.628Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":1291043239072,"suggestedFile":"Ornith-1.5-397B-Q4_K_M.gguf","requirements":{"ramGb":263,"diskBytes":244309803808,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:nvidia/nemotron-3.5-asr-streaming-0.6b","slug":"model-nvidia-nemotron-3-5-asr-streaming-0-6b","kind":"model","category":"speech","title":"nemotron-3.5-asr-streaming-0.6b","summary":"This model is the multilingual extension of nvidia/nemotron-speech-streaming-en-0.6b, adding language-ID prompt conditioning to support transcription across 40 language-locales from a single model.","source":{"provider":"hf","ref":"nvidia/nemotron-3.5-asr-streaming-0.6b","url":"https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b","rev":"ea30d66debe3740a08b573244286791d423d6b3e","fetchedAt":"2026-10-02T21:01:25.521Z","etag":"W/\"3069-o0CAvkXCE2R58wxzkSFf2dFpu1I\""},"author":{"name":"nvidia","url":"https://huggingface.co/nvidia"},"license":{"spdx":null,"raw":"other","url":"https://openmdw.ai/license/1-1/","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":1240287,"likes":1159,"takenAt":"2026-10-02T21:01:25.521Z"},"tags":["nemo","safetensors","gguf","nemotron3_5_asr","feature-extraction","transformers","speech-recognition","cache-aware ASR","automatic-speech-recognition","streaming-asr","multilingual","speech","audio","FastConformer","RNNT","Parakeet","ASR","pytorch","NeMo","en","es","de","fr","it","ar","ja","ko","pt","ru","hi","zh","vi","he","nl","cs","da","pl","no","sv","th"],"pipeline":"automatic-speech-recognition","links":{"github":"NVIDIA-NeMo/NeMo"},"updatedAt":"2026-09-10T16:49:07.000Z","collectedAt":"2026-10-02T21:01:25.521Z","review":{"numbers":["1,240,287 downloads on Hugging Face","1,159 likes","license other","0.7 GB for nemotron-3.5-asr-streaming-0.6b.q8_0.gguf"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:25.521Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":3294153408,"suggestedFile":"nemotron-3.5-asr-streaming-0.6b.q8_0.gguf","requirements":{"ramGb":2,"diskBytes":742090464,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"]}},{"v":1,"id":"model:hf:LiquidAI/LFM2.5-2.6B-GGUF","slug":"model-liquidai-lfm2-5-2-6b-gguf","kind":"model","category":"llm","title":"LFM2.5-2.6B-GGUF","summary":"LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.","source":{"provider":"hf","ref":"LiquidAI/LFM2.5-2.6B-GGUF","url":"https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF","rev":"e7caca5d835a3901a8e0d63e94009429bafafdfc","fetchedAt":"2026-10-02T20:59:26.626Z","etag":"W/\"29c3-yU7aErCK/t5EaBf7bR1fU7x7FlA\""},"author":{"name":"LiquidAI","url":"https://huggingface.co/LiquidAI"},"license":{"spdx":null,"raw":"other","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":1066051,"downloadsWeek":327838,"likes":360,"takenAt":"2026-10-02T20:59:26.626Z"},"tags":["gguf","safetensors","liquid","lfm2.5","llama.cpp","text-generation","ar","zh","en","fr","de","hi","id","it","ja","ko","pl","pt","ru","es","th","vi","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-09-22T20:42:43.000Z","collectedAt":"2026-10-02T20:59:26.626Z","review":{"numbers":["1,066,051 downloads on Hugging Face","360 likes","license other","1.6 GB for LFM2.5-2.6B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:26.626Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":33493525928,"suggestedFile":"LFM2.5-2.6B-Q4_K_M.gguf","requirements":{"ramGb":3,"diskBytes":1674455040,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:unsloth/GLM-5.3-Flash-GGUF","slug":"model-unsloth-glm-5-3-flash-gguf","kind":"model","category":"llm","title":"GLM-5.3-Flash-GGUF","summary":"Unsloth Dynamic 3.0 achieves superior accuracy & outperforms other leading quants.","source":{"provider":"hf","ref":"unsloth/GLM-5.3-Flash-GGUF","url":"https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF","rev":"621d456e93e926e4b52f85cff5f634358c1828f9","fetchedAt":"2026-10-02T20:59:29.613Z","etag":"W/\"85bb-FeDecc41pigAjyrvbfi0jI4nJEM\""},"author":{"name":"unsloth","url":"https://huggingface.co/unsloth"},"license":{"spdx":"mit","raw":"mit","open":true},"metrics":{"downloads":1012847,"downloadsWeek":327838,"likes":443,"takenAt":"2026-10-02T20:59:29.613Z"},"tags":["gguf","unsloth","glm5_next","text-generation","en","zh","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-09-06T06:55:24.000Z","collectedAt":"2026-10-02T20:59:29.613Z","review":{"numbers":["1,012,847 downloads on Hugging Face","443 likes","license mit","0.0 GB for Q8_0/GLM-5.3-Flash-Q8_0-00001-of-00008.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:29.613Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":2542718825045,"suggestedFile":"Q8_0/GLM-5.3-Flash-Q8_0-00001-of-00008.gguf","requirements":{"ramGb":1,"diskBytes":9429888,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:handy-computer/cohere-transcribe-03-2026-gguf","slug":"model-handy-computer-cohere-transcribe-03-2026-gguf","kind":"model","category":"speech","title":"cohere-transcribe-03-2026-gguf","summary":"cohere-transcribe-03-2026: transcribe.cpp GGUF","source":{"provider":"hf","ref":"handy-computer/cohere-transcribe-03-2026-gguf","url":"https://huggingface.co/handy-computer/cohere-transcribe-03-2026-gguf","rev":"ab667acedcb5d8d56837ef3ed3568c3ad50dde47","fetchedAt":"2026-10-02T21:01:28.531Z","etag":"W/\"ef6-CFGpeCT+Z1Er4gmeWd6e2kIOmVk\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":978058,"downloadsWeek":15195,"likes":3,"takenAt":"2026-10-02T21:01:28.531Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","cohere","conformer","encoder-decoder","multilingual","automatic-speech-recognition","en","fr","de","es","it","pt","nl","pl","el","ar","ja","zh","vi","ko"],"pipeline":"automatic-speech-recognition","links":{"github":"ggml-org/whisper.cpp","npm":"nodejs-whisper"},"updatedAt":"2026-09-15T07:05:31.000Z","collectedAt":"2026-10-02T21:01:28.531Z","review":{"numbers":["978,058 downloads on Hugging Face","3 likes","license apache-2.0","1.5 GB for cohere-transcribe-03-2026-Q4_K_M.gguf","15,195 npm downloads a week for nodejs-whisper","latest nodejs-whisper@0.3.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:28.531Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":15923521024,"suggestedFile":"cohere-transcribe-03-2026-Q4_K_M.gguf","requirements":{"ramGb":3,"diskBytes":1558162944,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"]}},{"v":1,"id":"model:hf:CMSManhattan/JiRackUltra_14b","slug":"model-cmsmanhattan-jirackultra-14b","kind":"model","category":"llm","title":"JiRackUltra_14b","summary":"JiRack Ultra 14B (CPU) A fast and efficient 14B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Media, Vision, Sou…","source":{"provider":"hf","ref":"CMSManhattan/JiRackUltra_14b","url":"https://huggingface.co/CMSManhattan/JiRackUltra_14b","rev":"1998717242fdacc84bcf10365e05d2de9639d79b","fetchedAt":"2026-10-02T20:59:32.622Z","etag":"W/\"a2ad-ZrAAXIY0ABekq64UhHeB/Fd/7Rs\""},"author":{"name":"CMSManhattan","url":"https://huggingface.co/CMSManhattan"},"license":{"spdx":"mit","raw":"mit","open":true},"metrics":{"downloads":963843,"downloadsWeek":327838,"likes":2,"takenAt":"2026-10-02T20:59:32.622Z"},"tags":["safetensors","gguf","qwen2","text-generation","ternary","bitnet","1.58bit","cpu","qwen2.5","deepseek","efficient","low-memory","jirack","web-ui","routing","tool-call","robotics","conversational","en","zh","ja","ko","fr","es","pt","de","it","ru","ar","vi","th","endpoints_compatible"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-10-01T18:11:59.000Z","collectedAt":"2026-10-02T20:59:32.622Z","review":{"numbers":["963,843 downloads on Hugging Face","2 likes","license mit","8.4 GB for JiRackUltra_14b_Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:32.622Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":153024234161,"suggestedFile":"JiRackUltra_14b_Q4_K_M.gguf","requirements":{"ramGb":11,"diskBytes":8988110048,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF","slug":"model-esatapedico-qwen3-8-27b-nvfp4-mtp-gguf","kind":"model","category":"llm","title":"Qwen3.8-27B-NVFP4-MTP-GGUF","summary":"A family of nine GGUF files of Qwen3.8-27B (the native vision-language 27B dense model, Gated DeltaNet + Gated Attention hybrid layout, 262,144-token native context, MTP speculative head), converted…","source":{"provider":"hf","ref":"esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF","url":"https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF","rev":"bcd7a7d3e251d4ec0fd15c72584b5eb9e0981383","fetchedAt":"2026-10-02T20:59:37.626Z","etag":"W/\"1440-B7NDxBfGxtt0KImhHBptHpugPOE\""},"author":{"name":"esatapedico","url":"https://huggingface.co/esatapedico"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":752373,"downloadsWeek":327838,"likes":115,"takenAt":"2026-10-02T20:59:37.626Z"},"tags":["gguf","nvfp4","qwen3.8","qwen3.5","blackwell","mtp","speculative-decoding","vision","multimodal","llama.cpp","text-generation","en","multilingual"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2026-08-22T00:11:17.000Z","collectedAt":"2026-10-02T20:59:37.626Z","review":{"numbers":["752,373 downloads on Hugging Face","115 likes","license apache-2.0","14 GB for Qwen3.8-27B-NVFP4-MTP-VERY-LOW.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:37.626Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":173362824480,"suggestedFile":"Qwen3.8-27B-NVFP4-MTP-VERY-LOW.gguf","requirements":{"ramGb":17,"diskBytes":14862277984,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF","slug":"model-yuxinlu1-gemma-4-12b-agentic-fable5-composer2-5-v2-3-5x-tau2-gguf","kind":"model","category":"llm","title":"gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF","summary":"💻🤖 Gemma4-12B v2 — Coding + Agentic Edition ✨ ### 🐣 Tiny footprint, big brain — a local coding & tool-using agent for everyone","source":{"provider":"hf","ref":"yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF","url":"https://huggingface.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF","rev":"190a31365a6b80a692349be34ccdac730cad4fe4","fetchedAt":"2026-10-02T20:59:41.761Z","etag":"W/\"52e0-bghZN/2OS4p1e/YBaF/Zjy0g1HQ\""},"author":{"name":"yuxinlu1","url":"https://huggingface.co/yuxinlu1"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":710251,"downloadsWeek":327838,"likes":1632,"takenAt":"2026-10-02T20:59:41.761Z"},"tags":["gguf","gemma4","coding","agentic","terminal","tool-use","reasoning","thinking","llama.cpp","local-llm","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"google-deepmind/gemma","npm":"node-llama-cpp"},"updatedAt":"2026-06-19T09:31:48.000Z","collectedAt":"2026-10-02T20:59:41.761Z","review":{"numbers":["710,251 downloads on Hugging Face","1,632 likes","license apache-2.0","6.9 GB for gemma4-v2-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:41.761Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":38112283520,"suggestedFile":"gemma4-v2-Q4_K_M.gguf","requirements":{"ramGb":9,"diskBytes":7381381664,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:empero-ai/Qwen3.8-9B-Distill-GGUF","slug":"model-empero-ai-qwen3-8-9b-distill-gguf","kind":"model","category":"llm","title":"Qwen3.8-9B-Distill-GGUF","summary":"GGUF quantizations of empero-ai/Qwen3.8-9B — a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-9B architecture — for llama.cpp, Ollama, LM Studio, Jan, KoboldCpp, and other stock GG…","source":{"provider":"hf","ref":"empero-ai/Qwen3.8-9B-Distill-GGUF","url":"https://huggingface.co/empero-ai/Qwen3.8-9B-Distill-GGUF","rev":"760121cd70bb4c36b2b5ec58eb765e0df5987efe","fetchedAt":"2026-10-02T20:59:44.409Z","etag":"W/\"2a85-NMsVJE6BdLoGjFcUMZp57A923S4\""},"author":{"name":"empero-ai","url":"https://huggingface.co/empero-ai"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":675501,"downloadsWeek":327838,"likes":286,"takenAt":"2026-10-02T20:59:44.409Z"},"tags":["gguf","llama.cpp","quantized","empero-ai","qwen3.5","qwen3.8","distillation","reasoning","gated-deltanet","text-generation","en","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2026-08-16T01:00:49.000Z","collectedAt":"2026-10-02T20:59:44.409Z","review":{"numbers":["675,501 downloads on Hugging Face","286 likes","license apache-2.0","5.4 GB for Qwen3.8-9B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:44.409Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":48174916160,"suggestedFile":"Qwen3.8-9B-Q4_K_M.gguf","requirements":{"ramGb":7,"diskBytes":5780090176,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:FINAL-Bench/POCKET-35B-GGUF","slug":"model-final-bench-pocket-35b-gguf","kind":"model","category":"llm","title":"POCKET-35B-GGUF","summary":"🆕 POCKET-Qwen3.8-Flash-Next — a 180B model running on a laptop with 8 GB VRAM + 32 GB RAM · 4.17 tok/s measured. >","source":{"provider":"hf","ref":"FINAL-Bench/POCKET-35B-GGUF","url":"https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF","rev":"c9e42c51357fdd5f25af7cd7dc0e8bf59c81af4d","fetchedAt":"2026-10-02T20:59:47.536Z","etag":"W/\"2c60-7oLChP/CcR6mOOjR9OT+0enKXN0\""},"author":{"name":"FINAL-Bench","url":"https://huggingface.co/FINAL-Bench"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":669265,"downloadsWeek":327838,"likes":81,"takenAt":"2026-10-02T20:59:47.536Z"},"tags":["llama.cpp","gguf","conversational","on-device","mobile","iphone","android","cpu","local-llm","edge","mixture-of-experts","moe","quantized","pocket","vidraft","qwen3_5_moe","darwin","text-generation","endpoints_compatible","imatrix"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-09-25T12:53:11.000Z","collectedAt":"2026-10-02T20:59:47.536Z","review":{"numbers":["669,265 downloads on Hugging Face","81 likes","license apache-2.0","20 GB for POCKET-35B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:47.536Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":59110323456,"suggestedFile":"POCKET-35B-Q4_K_M.gguf","requirements":{"ramGb":24,"diskBytes":21166757568,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:empero-ai/Qwen3.8-4B-Distill-GGUF","slug":"model-empero-ai-qwen3-8-4b-distill-gguf","kind":"model","category":"llm","title":"Qwen3.8-4B-Distill-GGUF","summary":"GGUF quantizations of empero-ai/Qwen3.8-4B — a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-4B architecture — for llama.cpp, Ollama, LM Studio, Jan, KoboldCpp, and other stock GG…","source":{"provider":"hf","ref":"empero-ai/Qwen3.8-4B-Distill-GGUF","url":"https://huggingface.co/empero-ai/Qwen3.8-4B-Distill-GGUF","rev":"391fc7d103e3942a408def3e4f51c2f85d464417","fetchedAt":"2026-10-02T20:59:50.539Z","etag":"W/\"2a82-XH740FLFJYyNGY4Qisz3qBKJOIY\""},"author":{"name":"empero-ai","url":"https://huggingface.co/empero-ai"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":666186,"downloadsWeek":327838,"likes":161,"takenAt":"2026-10-02T20:59:50.539Z"},"tags":["gguf","llama.cpp","quantized","empero-ai","qwen3.5","qwen3.8","distillation","reasoning","gated-deltanet","text-generation","en","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2026-08-16T01:00:50.000Z","collectedAt":"2026-10-02T20:59:50.539Z","review":{"numbers":["666,186 downloads on Hugging Face","161 likes","license apache-2.0","2.6 GB for Qwen3.8-4B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:50.539Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":22784098720,"suggestedFile":"Qwen3.8-4B-Q4_K_M.gguf","requirements":{"ramGb":4,"diskBytes":2783446304,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:AtomicChat/Qwen3.8-Flash-Next-GGUF","slug":"model-atomicchat-qwen3-8-flash-next-gguf","kind":"model","category":"llm","title":"Qwen3.8-Flash-Next-GGUF","summary":"Built from Qwen's original weights with our own importance matrix. The calibration corpora behind our builds are public.","source":{"provider":"hf","ref":"AtomicChat/Qwen3.8-Flash-Next-GGUF","url":"https://huggingface.co/AtomicChat/Qwen3.8-Flash-Next-GGUF","rev":"142262902a46f7daed19c79d0771534c8106ad59","fetchedAt":"2026-10-02T20:59:53.544Z","etag":"W/\"a1aa-cp8JBzveQdXzNBQ2mZXqLO6UBNg\""},"author":{"name":"AtomicChat","url":"https://huggingface.co/AtomicChat"},"license":{"spdx":null,"raw":"other","url":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/main/LICENSE","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":634102,"downloadsWeek":327838,"likes":170,"takenAt":"2026-10-02T20:59:53.544Z"},"tags":["gguf","atomic-chat","qwen","qwen3.8","flash-next","moe","multimodal","imatrix","quantized","llama.cpp","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2026-08-27T01:36:22.000Z","collectedAt":"2026-10-02T20:59:53.544Z","review":{"numbers":["634,102 downloads on Hugging Face","170 likes","license other","0.5 GB for imatrix.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:53.544Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":292373376224,"suggestedFile":"imatrix.gguf","requirements":{"ramGb":2,"diskBytes":580038688,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}},{"v":1,"id":"model:hf:prism-ml/Ternary-Bonsai-27B-gguf","slug":"model-prism-ml-ternary-bonsai-27b-gguf","kind":"model","category":"llm","title":"Ternary-Bonsai-27B-gguf","summary":"Prism ML Website Whitepaper Demo & Examples Discord","source":{"provider":"hf","ref":"prism-ml/Ternary-Bonsai-27B-gguf","url":"https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf","rev":"86e89f34c93201c3dfd5e5880fedb0022fc7e34d","fetchedAt":"2026-10-02T20:59:56.553Z","etag":"W/\"3060-46+OtwY9FOwscj2ZNpwXIjFZtOQ\""},"author":{"name":"prism-ml","url":"https://huggingface.co/prism-ml"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":628497,"downloadsWeek":327838,"likes":1403,"takenAt":"2026-10-02T20:59:56.553Z"},"tags":["llama.cpp","gguf","conversational","ternary","2-bit","llama-cpp","cuda","metal","on-device","hybrid-attention","prismml","bonsai","text-generation","eval-results","endpoints_compatible"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-08-31T22:04:46.000Z","collectedAt":"2026-10-02T20:59:56.553Z","review":{"numbers":["628,497 downloads on Hugging Face","1,403 likes","license apache-2.0","50 GB for Ternary-Bonsai-27B-F16.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:56.553Z","http":200},"install":{"kind":"model","format":"gguf","gated":false,"totalBytes":86522526080,"suggestedFile":"Ternary-Bonsai-27B-F16.gguf","requirements":{"ramGb":59,"diskBytes":53808280640,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"]}}],"total":136,"next":24,"generatedAt":"2026-10-02T21:01:49.857Z"}