Voxtral-Mini-4B-Realtime-2602 needs about 4.0 GB of memory at Q4_K (a 3.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 3.1 GB (Q4_K) to 5.1 GB (Q8_0).
Voxtral Mini 4B Realtime ASR in GGUF format
Voxtral Mini 4B Realtime is a 4‑billion parameter audio model for speech recognition. It is packaged as a single GGUF file and runs locally with audio.cpp. The model supports offline and streaming ASR.
Good at
- Fast inference on GPUs
- Low‑latency streaming
- Accurate transcription
Limits
- No vision or multimodal support
- No license information provided
- Requires audio.cpp framework
Best for
- Real‑time voice assistants
- Transcribing short audio clips
- Local speech-to-text pipelines
Who it’s for. Developers and researchers needing a lightweight, locally deployable ASR model. It is suitable for embedded systems and low‑resource environments where GPU memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q8_0 | 5.1 GB | 6.2 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K quantization (3.1 GB file, ~4 GB memory at 8k context). For higher accuracy and more memory, use Q8_0 (5.1 GB file, ~6.2 GB memory).
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 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 (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K (3.1 GB file, about 4.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.1 GB file, about 6.2 GB in use).
Which Voxtral-Mini-4B-Realtime-2602 quant should you choose?
Q4_K (3.1 GB) is the middle option in this repository. 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
Frequently asked questions about Voxtral-Mini-4B-Realtime-2602
How much VRAM does Voxtral-Mini-4B-Realtime-2602 need?
About 4.0 GB at Q4_K with an 8K context window. That is the 3.1 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 5.1 GB file needs about 6.2 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 is 3.1 GB, Q8_0 is 5.1 GB.
Where can I download Voxtral-Mini-4B-Realtime-2602 GGUF?
The files are on Hugging Face in the mistral-experimental/AudioCPP-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.
Can I run Voxtral Mini 4B Realtime on 8 GB VRAM?
Yes, the Q4_K quantization requires about 4 GB of VRAM at 8k context, fitting within an 8 GB GPU.
Does this model support multi‑language transcription?
The model’s language support is not specified; no language list is provided.
What framework is needed to run this model?
audio.cpp is required; the GGUF file contains all necessary specifications for local inference.