Model Intelligence Sheet
ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF overview
Voxtral Mini 4B Realtime 2602 Run it in the Llama app: https://llama.app Or from the terminal: bash llama serve hf ggml org/Voxtral Mini 4B Realtime 2602 GGUF …
Runs locally from ~1014.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
5 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Voxtral-Mini-4B-Realtime-2602-BF16.gguf | GGUF | BF16 | 6.40 GB | Download |
| Voxtral-Mini-4B-Realtime-2602-Q4_K_M.gguf | GGUF | Q4_K_M | 2.38 GB | Download |
| Voxtral-Mini-4B-Realtime-2602-Q8_0.gguf | GGUF | Q8_0 | 3.41 GB | Download |
| mmproj-Voxtral-Mini-4B-Realtime-2602-BF16.gguf | GGUF | BF16 | 1.85 GB | Download |
| mmproj-Voxtral-Mini-4B-Realtime-2602-Q8_0.gguf | GGUF | Q8_0 | 1014.5 MB | Download |
Model Details
| Model ID | ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF |
|---|---|
| Author | ggml-org |
| Pipeline | automatic-speech-recognition |
| License | apache-2.0 |
| Base model | mistralai/Voxtral-Mini-4B-Realtime-2602 |
| Last modified | 2026-10-19T15:47:13.000Z |
Model README
---
license: apache-2.0
pipeline_tag: automatic-speech-recognition
tags:
- gguf
- quantized
base_model:
- mistralai/Voxtral-Mini-4B-Realtime-2602
---
Voxtral-Mini-4B-Realtime-2602
Run it in the Llama app: https://llama.app
Or from the terminal:
llama serve -hf ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUFThis is a realtime (streaming) speech recognition model. See https://github.com/ggml-org/llama.cpp/pull/30629
Source models
- https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602
> [!IMPORTANT]
> This model is automatically converted using https://github.com/ggml-org/convert
Run ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models