Voxtral-Mini-4B-Realtime-2602 needs about 3.9 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 2.6 GB (Q4_K_M) to 6.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Voxtral Mini 4B Realtime 2602 – multilingual, realtime speech‑transcription
Voxtral Mini 4B Realtime 2602 is a multilingual, realtime speech‑transcription model based on the Mistral3 architecture. It supports audio streaming via vLLM and can process up to 131072 context tokens, roughly 3 hours of continuous speech.
Good at
- Realtime speech transcription
- Multilingual audio support
- Low‑latency streaming
Limits
- No vision support
- Requires vLLM for operation
- Limited to 131072 context tokens
Best for
- Live captioning
- Audio transcription pipelines
- Real‑time voice assistants
Who it’s for. Developers building real‑time audio applications who need an open‑source, low‑latency transcription model. The model is suitable for production use with vLLM and supports streaming via websockets.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.6 GB | 3.9 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 5.0 GB | Fits | Get file → | |
| BF16 | 6.9 GB | 8.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.55 GB, estimated memory 3.9 GB at 8 k context). If more memory is available, Q8_0 (3.66 GB, 5 GB memory) provides higher precision. BF16 (6.88 GB, 8.2 GB memory) requires at least 8 GB VRAM and is best for maximum accuracy.
What GPU do you need for Voxtral-Mini-4B-Realtime-2602?
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 Q4_K_M (2.6 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.9 GB file, about 8.2 GB in use).
Which Voxtral-Mini-4B-Realtime-2602 quant should you choose?
Q4_K_M is the usual starting point for Voxtral-Mini-4B-Realtime-2602: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 3.7 GB, about 1.4 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 Voxtral-Mini-4B-Realtime-2602
How much VRAM does Voxtral-Mini-4B-Realtime-2602 need?
About 3.9 GB at Q4_K_M with an 8K context window. That is the 2.6 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 Voxtral-Mini-4B-Realtime-2602 on an 8 GB GPU?
Yes, with Q8_0: the 3.7 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Voxtral-Mini-4B-Realtime-2602 GGUF?
It depends on the quant: Q4_K_M is 2.6 GB, Q8_0 is 3.7 GB, BF16 is 6.9 GB.
What context length does Voxtral-Mini-4B-Realtime-2602 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.
Where can I download Voxtral-Mini-4B-Realtime-2602 GGUF?
The files are on Hugging Face in the ggml-org/Voxtral-Mini-4B-Realtime-2602-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 Voxtral-Mini-4B-Realtime-2602 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 Voxtral Mini 4B Realtime on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 3.9 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does the model support vision tasks?
No, Voxtral Mini 4B Realtime only supports speech‑transcription and does not include vision capabilities.
What is the maximum continuous recording length?
The model can handle up to 131072 context tokens, roughly 3 hours of continuous speech, before requiring a reset.