{"v":1,"id":"model:hf:superwhisper/s1-mini-GGUF","slug":"model-superwhisper-s1-mini-gguf","kind":"model","category":"llm","title":"s1-mini-GGUF","summary":"GGUF builds of superwhisper/s1-mini, release v1, for llama.cpp, Ollama, LM Studio, and anything else built on llama.cpp. You can use it in your own dictation app too, just check the license first.","source":{"provider":"hf","ref":"superwhisper/s1-mini-GGUF","url":"https://huggingface.co/superwhisper/s1-mini-GGUF","rev":"34add00a48a2e5d24e5a4ee5405a99620a3a240c","fetchedAt":"2026-10-09T19:01:18.163Z","etag":"W/\"1b9b-Se81q5o19r/QMV1Xpqbx+v7fnAM\""},"author":{"name":"superwhisper","url":"https://huggingface.co/superwhisper"},"license":{"spdx":null,"raw":"other","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":277684,"downloadsWeek":15664,"likes":41,"stars":54249,"openIssues":352,"lastRelease":{"tag":"v1.9.5","at":"2026-10-06T17:39:17Z"},"pushedAt":"2026-10-06T17:39:15Z","takenAt":"2026-10-09T19:01:18.163Z"},"tags":["gguf","asr","automatic-speech-recognition","text-normalization","inverse-text-normalization","punctuation","truecasing","speech-to-text","dictation","post-processing","qwen3","llama.cpp","text-generation","en","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/whisper.cpp","npm":"nodejs-whisper"},"updatedAt":"2026-08-28T14:00:47.000Z","collectedAt":"2026-10-09T19:01:18.163Z","review":{"numbers":["277,684 downloads on Hugging Face","41 likes","license other","0.5 GB for s1-mini-q4_k_m.gguf","54,249 stars on ggml-org/whisper.cpp","352 open issues and PRs","last release v1.9.5 on 2026-10-06","15,664 npm downloads a week for nodejs-whisper","latest nodejs-whisper@0.3.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-09T19:01:18.163Z","http":200},"description":"# S1-mini-GGUF by [Superwhisper](https://superwhisper.com)\n\n  [](https://superwhisper.com)\n  [](https://discord.gg/tF98XvJNvB)\n  [](https://huggingface.co/superwhisper/s1-mini-GGUF/tree/v1)\n\nGGUF builds of [superwhisper/s1-mini](https://huggingface.co/superwhisper/s1-mini),\nrelease v1, for llama.cpp, Ollama, LM Studio, and anything else built on\nllama.cpp. You can use it in your own dictation app too, just check the\nlicense first.\n\nS1-mini is a 0.6B-parameter text normalizer for speech-to-text output. It\ntakes a raw ASR transcript and rewrites it as clean written text: fillers\nremoved, false starts and self-corrections resolved to the value the speaker\nlanded on, punctuation and capitalization applied, and spoken numbers, dates,\ntimes, currency and email addresses rendered in written form.\n\nAt Q4_K_M it is a 462 MiB file that runs comfortably on a laptop CPU, and on a\nheld-out set of 7,519 English cases it reaches 94.8% token accuracy.\n\nThe model covers English only. It is not a chat model and will not follow\ngeneral instructions; it does one job, and you steer it with a control line at\nthe top of the input. Full documentation lives in the\n[BF16 repository](https://huggingface.co/superwhisper/s1-mini).\n\n## Files\n\n| File | Type | Size | Notes |\n|---|---|---|---|\n| `s1-mini-q4_k_m.gguf` | Q4_K_M | 462 MB | Recommended. The build the published accuracy was measured on. |\n| `s1-mini-f16.gguf` | F16 | 1.4 GB | Unquantized conversion, the intermediate the Q4_K_M is produced from. |\n\nBoth files share the same skeleton: architecture `qwen3`, 311 tensors, 28\nblocks, a 40,960-token context window, and an embedded chat template. The\nQ4_K_M build keeps the most quantization-sensitive tensors at Q6_K (29 of 311)\nand the bulk at Q4_K, while normalization parameters stay F32 in both builds.\n\n> [!NOTE]\n> The Hub sidebar reports 0.8B parameters for this repo. Qwen3-0.6B sets\n> `tie_word_embeddings`, but ships `lm_head.weight…\n\nSource: https://huggingface.co/superwhisper/s1-mini-GGUF","install":{"kind":"model","hfId":"superwhisper/s1-mini-GGUF","gated":false,"format":"gguf","files":[{"name":"s1-mini-f16.gguf","size":1509347232,"quant":"F16","sha256":"0370da4f1bae19e3150bcafa33c5d396c15f97bf25519540a3e013db5cc00af4"},{"name":"s1-mini-q4_k_m.gguf","size":484219808,"quant":"Q4_K_M","sha256":"3b41ebe2502cbd03e811d5d16b022f5ab551eda58d62597d152f89535003c634"}],"totalBytes":1993567040,"suggestedFile":"s1-mini-q4_k_m.gguf","requirements":{"ramGb":2,"diskBytes":484219808,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"],"command":"lsh models install hf:superwhisper/s1-mini-GGUF"}}