{"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},"description":"# nemotron-3.5-asr-streaming-0.6b: transcribe.cpp GGUF\n\nGGUF conversions of [nvidia/nemotron-3.5-asr-streaming-0.6b](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b) for use\nwith [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).\n\nPorted from upstream commit\n[24b151a](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b/commit/24b151a),\npinned 2026-06-08.\nValidated against the NeMo reference at transcribe.cpp commit\n[909e94e](https://github.com/handy-computer/transcribe.cpp/tree/909e94e)\non 2026-06-08.\n\nMultilingual speech-to-text across 32 supported language-locales (the model's tokenizer recognizes 40, but 8 are adaptation-ready and need fine-tuning) with punctuation and capitalization. A 0.6B-parameter cache-aware streaming FastConformer encoder with a prompt-conditioned RNN-T transducer decoder; the target language is selected per call (--language en-US, fr-FR, de-DE, ...) and an auto mode emits a  tag. Ships both the offline path (att_context_size=[56, 13], 1.12s, headline accuracy) and runtime-selectable chunked streaming (--stream-chunk-ms 1120 --stream-att-right {0,3,6,13}).\n\n## Downloads\n\n| Quantization | Download | Size | WER (FLEURS test en (en-US), offline att_context_size=[56, 13]) |\n| --- | --- | ---: | ---: |\n| F32 | [nemotron-3.5-asr-streaming-0.6b-F32.gguf](https://huggingface.co/handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf/resolve/main/nemotron-3.5-asr-streaming-0.6b-F32.gguf) | 2.55 GB | 7.97% |\n| F16 | [nemotron-3.5-asr-streaming-0.6b-F16.gguf](https://huggingface.co/handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf/resolve/main/nemotron-3.5-asr-streaming-0.6b-F16.gguf) | 1.28 GB | 7.97% |\n| Q8_0 | [nemotron-3.5-asr-streaming-0.6b-Q8_0.gguf](https://huggingface.co/handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf/resolve/main/nemotron-3.5-asr-streaming-0.6b-Q8_0.gguf) | 751 MB | 7.88% |\n| Q6_K | [nemotron-3.5-asr…\n\nSource: https://huggingface.co/handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf","install":{"kind":"model","hfId":"handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf","gated":false,"format":"gguf","files":[{"name":"nemotron-3.5-asr-streaming-0.6b-F16.gguf","size":1277750240,"quant":"F16","sha256":"f21a0cea64d232981def7f8f2b7ab322459703a2e89359962c042c57159755b1"},{"name":"nemotron-3.5-asr-streaming-0.6b-F32.gguf","size":2552277984,"quant":"F32","sha256":"fbbc82e8e1084301a670fbc4d79c69c0c8980da506352fd83e74a182f38f5b78"},{"name":"nemotron-3.5-asr-streaming-0.6b-Q4_K_M.gguf","size":495831520,"quant":"Q4_K_M","sha256":"41c99fa5fb6f3d35f68e79adc3e755eca2232a8d921178bd647b71194792b8fd"},{"name":"nemotron-3.5-asr-streaming-0.6b-Q5_K_M.gguf","size":559647200,"quant":"Q5_K_M","sha256":"86429e8c4f7fdcf9b3312269ad1ca6669478ba7805331c4aea7a2e33e9910d65"},{"name":"nemotron-3.5-asr-streaming-0.6b-Q6_K.gguf","size":621356512,"quant":"Q6_K","sha256":"4ff802c6207c4a7df23242003fd2aa849a1ab02bba6bc80c3db02e7e82606c28"},{"name":"nemotron-3.5-asr-streaming-0.6b-Q8_0.gguf","size":751094240,"quant":"Q8_0","sha256":"b94545b313b3223fda7b2857a52681da813935c2127643d1e9ff0c23d988089c"}],"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"],"command":"lsh models install hf:handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf"}}