{"v":1,"id":"model:hf:handy-computer/granite-speech-4.1-2b-gguf","slug":"model-handy-computer-granite-speech-4-1-2b-gguf","kind":"model","category":"speech","title":"granite-speech-4.1-2b-gguf","summary":"granite-speech-4.1-2b: transcribe.cpp GGUF","source":{"provider":"hf","ref":"handy-computer/granite-speech-4.1-2b-gguf","url":"https://huggingface.co/handy-computer/granite-speech-4.1-2b-gguf","rev":"5fa89dfac74d52a186f63647553b9e1f7ae36e83","fetchedAt":"2026-10-02T21:00:16.371Z","etag":"W/\"ef2-+g64vRMEQBbadFbhx9N/F8E1Xh0\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":35838,"downloadsWeek":15195,"likes":0,"takenAt":"2026-10-02T21:00:16.371Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","granite","granite-speech","audio-llm","multilingual","automatic-speech-recognition","en","fr","de","es","pt","ja","conversational"],"pipeline":"automatic-speech-recognition","links":{"github":"ggml-org/whisper.cpp","npm":"nodejs-whisper"},"updatedAt":"2026-09-27T05:58:04.000Z","collectedAt":"2026-10-02T21:00:16.371Z","review":{"numbers":["35,838 downloads on Hugging Face","0 likes","license apache-2.0","1.5 GB for granite-speech-4.1-2b-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":"2026-10-02T21:00:16.371Z","http":200},"description":"# granite-speech-4.1-2b: transcribe.cpp GGUF\n\nGGUF conversions of [ibm-granite/granite-speech-4.1-2b](https://huggingface.co/ibm-granite/granite-speech-4.1-2b) for use\nwith [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).\n\nPorted from upstream commit\n[8f4bb5f](https://huggingface.co/ibm-granite/granite-speech-4.1-2b/commit/8f4bb5f),\npinned 2026-05-17.\nValidated against the Transformers reference at transcribe.cpp commit\n[275332d](https://github.com/handy-computer/transcribe.cpp/tree/275332d)\non 2026-05-17.\n\nOffline multilingual speech-to-text. IBM Granite Speech 4.1-2b is an\naudio-LLM with the same architecture as 4.0-1b (Conformer encoder with\nblock-local Shaw attention, BLIP-2 Q-Former projector, Granite-4.0-1b-base\nautoregressive LLM decoder) and improved punctuation and casing over 4.0-1b.\nTakes a 16 kHz mono WAV and produces a transcript. Transcribes English,\nFrench, German, Spanish, Portuguese, and Japanese. Translates between\nEnglish and each of those five other languages in either direction\n(en ↔ fr, en ↔ de, en ↔ es, en ↔ pt, en ↔ ja) — always via English, no\ndirect fr↔de etc.\n\n## Downloads\n\n| Quantization | Download | Size | WER (LibriSpeech test-clean) |\n| --- | --- | ---: | ---: |\n| BF16 | [granite-speech-4.1-2b-BF16.gguf](https://huggingface.co/handy-computer/granite-speech-4.1-2b-gguf/resolve/main/granite-speech-4.1-2b-BF16.gguf) | 4.63 GB | 1.31% |\n| F16 | [granite-speech-4.1-2b-F16.gguf](https://huggingface.co/handy-computer/granite-speech-4.1-2b-gguf/resolve/main/granite-speech-4.1-2b-F16.gguf) | 4.63 GB | 1.32% |\n| Q8_0 | [granite-speech-4.1-2b-Q8_0.gguf](https://huggingface.co/handy-computer/granite-speech-4.1-2b-gguf/resolve/main/granite-speech-4.1-2b-Q8_0.gguf) | 2.56 GB | 1.32% |\n| Q6_K | [granite-speech-4.1-2b-Q6_K.gguf](https://huggingface.co/handy-computer/granite-speech-4.1-2b-gguf/resolve/main/granite-speech-4.1-2b-Q6_K.gguf) | 2.02 GB | 1.29% |\n|…\n\nSource: https://huggingface.co/handy-computer/granite-speech-4.1-2b-gguf","install":{"kind":"model","hfId":"handy-computer/granite-speech-4.1-2b-gguf","gated":false,"format":"gguf","files":[{"name":"granite-speech-4.1-2b-BF16.gguf","size":4631640192,"quant":"BF16","sha256":"8d1289a4e5effeb82c99d3c34ab84ac3589afb49397471489b6f31613c160233"},{"name":"granite-speech-4.1-2b-F16.gguf","size":4632623200,"quant":"F16","sha256":"0da20adff483987c6a1e8afa0b35bc812dbc8673acd00c98ecd9cf4c1e40f2b0"},{"name":"granite-speech-4.1-2b-Q4_K_M.gguf","size":1602904896,"quant":"Q4_K_M","sha256":"a7e92314cdff11a095024a3fc35ad3fffd637455b3f6764ffa54d7411d653d3c"},{"name":"granite-speech-4.1-2b-Q5_K_M.gguf","size":1829704640,"quant":"Q5_K_M","sha256":"1ea15c2174b485b8de81337a1da3ae6703a7892a5330345b9a2212e9a6a0c365"},{"name":"granite-speech-4.1-2b-Q6_K.gguf","size":2024968032,"quant":"Q6_K","sha256":"37585ad793ad03fd7d72f3daa490364130074e2d401a4ee9f5ca5b8f3f572c41"},{"name":"granite-speech-4.1-2b-Q8_0.gguf","size":2559878944,"quant":"Q8_0","sha256":"666d2f7736bfa140f44d67ba7bcb0827aa5718462f13850af294d72c1f09b218"}],"totalBytes":17281719904,"suggestedFile":"granite-speech-4.1-2b-Q4_K_M.gguf","requirements":{"ramGb":3,"diskBytes":1602904896,"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/granite-speech-4.1-2b-gguf"}}