Granite Speech 4.1 2b Plus needs about 2.2 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.0 GB (Q4_K_M) to 3.3 GB (BF16).
Granite Speech 4.1 2b Plus – 1.63B parameter ASR model with speaker attribution and word‑level timing
Granite Speech 4.1 2b Plus is a 1.63B parameter model trained for automatic speech recognition. It supports speaker‑attributed ASR and word‑level timestamps but does not provide punctuation or capitalization. The model is available in multiple GGUF quantizations.
Good at
- Speaker‑attributed ASR
- Word‑level timing
- Keyword‑biased recognition
Limits
- No punctuation or capitalization
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Transcribing multi‑speaker meetings
- Generating time‑coded subtitles
- Keyword‑based audio search
Who it’s for. Developers building speech‑to‑text pipelines that need speaker tags and precise timestamps. Researchers needing a lightweight ASR model with community‑requested features.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_M | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.6 GB | Fits | Get file → | |
| BF16 | 3.3 GB | 4.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.02 GB, ~2.2 GB memory) or Q5_K_M (1.18 GB, ~2.3 GB). For 16 GB VRAM, Q6_K (1.34 GB, ~2.5 GB) or Q8_0 (1.74 GB, ~2.9 GB) are suitable. BF16 (3.27 GB, ~4.4 GB) requires larger memory but offers higher precision.
What GPU do you need for Granite Speech 4.1 2b Plus?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q8_0 (1.7 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.3 GB file, about 4.4 GB in use).
Which Granite Speech 4.1 2b Plus quant should you choose?
Q4_K_M is the usual starting point for Granite Speech 4.1 2b Plus: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Granite Speech 4.1 2b Plus
How much VRAM does Granite Speech 4.1 2b Plus need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Plus on an 8 GB GPU?
Yes, with BF16: the 3.3 GB file needs about 4.4 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 Plus GGUF?
It depends on the quant: Q4_K_M is 1.0 GB, Q5_K_M is 1.2 GB, Q6_K is 1.3 GB, Q8_0 is 1.7 GB, BF16 is 3.3 GB.
What context length does Granite Speech 4.1 2b Plus support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.3 GB at 4K.
Where can I download Granite Speech 4.1 2b Plus GGUF?
The files are on Hugging Face in the ibm-granite/granite-speech-4.1-2b-plus-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 Plus 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 Plus on 8 GB VRAM?
Yes, the Q4_K_M quantization is 1.02 GB and requires about 2.2 GB VRAM at 8k context.
Does this model provide punctuation?
No, the plus variant does not provide punctuation or capitalization.
What license applies to this model?
The model is released under the Apache‑2.0 license.