granite speech 4.1 2b needs about 3.0 GB of memory at Q4_K (a 2.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.8 GB (Q4_K) to 5.6 GB (F16).
Granite Speech 4.1 2B – compact multilingual ASR and AST model
Granite Speech 4.1 2B is a 2.31‑billion‑parameter speech‑LLM designed for multilingual automatic speech recognition and bidirectional speech translation. It supports English, French, German, Spanish, Portuguese and Japanese, and includes dual‑head CTC encoder for transcription accuracy.
Good at
- Multilingual ASR
- Bidirectional speech translation
- Keyword‑biased recognition
Limits
- No vision support
- Requires 8‑k context for memory estimates
- Apache‑2.0 license
Best for
- Speech‑to‑text pipelines
- Multilingual transcription services
- Keyword‑biased ASR tasks
Who it’s for. Developers building speech‑to‑text or translation applications that need a lightweight, multilingual model. The model is suitable for edge or low‑resource deployments where disk space and VRAM are limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q4_K | 2.3 GB | 3.0 GB | Fits | Get file → | |
| Q4_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| F16 | 5.6 GB | 6.8 GB | Fits | Get file → |
For 8‑GB VRAM, use the Q4_K file (1.78 GB, ~2.5 GB memory at 8k context). If 12‑GB VRAM is available, the larger Q4_K (2.27 GB, ~3 GB memory) is recommended. For maximum quality with 16‑GB VRAM, the F16 file (5.58 GB, ~6.8 GB memory) can be used.
What GPU do you need for granite speech 4.1 2b?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K (2.9 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K (2.9 GB file, about 3.8 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 6.8 GB in use).
Which granite speech 4.1 2b quant should you choose?
Q4_K (2.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_K at 1.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about granite speech 4.1 2b
How much VRAM does granite speech 4.1 2b need?
About 3.0 GB at Q4_K with an 8K context window. That is the 2.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run granite speech 4.1 2b on an 8 GB GPU?
Yes, with F16: the 5.6 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of granite speech 4.1 2b GGUF?
It depends on the quant: Q4_K is 1.8 GB, Q4_K is 2.3 GB, Q4_K is 2.9 GB, F16 is 5.6 GB.
Where can I download granite speech 4.1 2b GGUF?
The files are on Hugging Face in the cstr/granite-speech-4.1-2b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does granite speech 4.1 2b use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Granite Speech 4.1 2B on 8 GB VRAM?
Yes, the Q4_K quantized file is 1.78 GB and requires about 2.5 GB of VRAM at 8k context.
Does this model support Japanese?
Yes, it supports Japanese along with English, French, German, Spanish and Portuguese.
What license applies to this model?
The model is released under the Apache‑2.0 license.