Granite Speech 4.1 2b GGUF

--- license: apache-2.0 base_model: ibm-granite/granite-speech-4.1-2b base_model_relation: quantized library_name: transcribe.cpp pipeline_tag: automatic-speech-recognition language: - en - fr - de - es - pt - ja tags: - gguf - transcribe.cpp - asr - speech-to-text - granite - granite-speech - audio-llm - multilingual transcribe_cpp: wer_librispeech_test_clean: bf16: 1.31 f16: 1.32 q8_0: 1.32 q6_k: 1.29 q5_k_m: 1.33 q4_k_m: 1.37 rtf_m4_max: metal: 33 cpu: 5.8 rtf_m4: metal: 12 cpu: 4 rtf_ryzen_4750u: vulkan: 2.8 cpu: 1.4 streaming: false translate: true lang_detect: false timestamps: none --- # granite-speech-4.1-2b: transcribe.cpp GGUF GGUF conversions of [ibm-granite/granite-speech-4.1-2b](https://huggingface.co/ibm-granite/granite-speech-4.1-2b) for use with [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp). Ported from upstream commit [8f4bb5f](https://huggingface.co/ibm-granite/granite-speech-4.1-2b/commit/8f4bb5f), pinned 2026-05-17. Validated against the Transformers reference at transcribe.cpp commit [275332d](https://github.com/handy-computer/transcribe.cpp/tree/275332d) on 2026-05-17. Offline multilingual speech-to-text. IBM Granite Speech 4.1-2b is an audio-LLM with the same architecture as 4.0-1b (Conformer encoder with block-local Shaw attention, BLIP-2 Q-Former projector, Granite-4.0-1b-base autoregressive LLM decoder) and improved punctuation and casing over 4.0-1b. Takes a 16 kHz mono WAV and produces a transcript. Transcribes English, French, German, Spanish, Portuguese, and Japanese. Translates between English and each of those five other languages in either direction (en ↔ fr, en ↔ de, en ↔ es, en ↔ pt, en ↔ ja) — always via English, no direct fr↔de etc. ## Downloads | Quantization | Download | Size | WER (LibriSpeech test-clean) | | --- | --- | ---: | ---: | | 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% | | 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% | | 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% | | Q6_K | [gr...

Source context: 1 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transcribe.cpp · Repo memoravox/granite-speech-4.1-2b-gguf