MI

Voxtral Mini 3B 2507

MistralGGUF by bartowskiUpdated 2025-07-28
Download on Hugging Face
Parameters4.01B
Context128K
Layers30
Architecturellama
Smallest quant0.0 GB
Quick answer

Voxtral Mini 3B 2507 needs about 4.0 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 8.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.

Voxtral Mini 3B 2507 – a compact multimodal model with audio and text capabilities

Voxtral Mini 3B 2507 is a 4.01 billion‑parameter model built on the Mistral architecture. It supports vision and audio input, offering speech transcription, translation, and audio understanding. The model retains strong text performance from its parent, Ministral‑3B.

Good at

  • Speech transcription and translation
  • Audio‑based Q&A and summarization
  • Multilingual audio understanding

Limits

  • No vision support beyond audio
  • Requires 8 k context for memory estimates
  • Apache‑2.0 license limits commercial use without attribution

Best for

  • Transcribing long audio files
  • Building voice‑activated assistants
  • Generating audio summaries

Who it’s for. Developers and researchers needing a lightweight multimodal model for speech and text tasks. The model is suitable for edge deployments where memory is limited but audio processing is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.5 GB
Fits Get file →
IQ2_M1.6 GB 3.1 GB
Fits Get file →
Q2_K1.7 GB 3.2 GB
Fits Get file →
IQ3_XXS1.7 GB 3.2 GB
Fits Get file →
IQ3_XS1.8 GB 3.3 GB
Fits Get file →
Q3_K_S1.9 GB 3.4 GB
Fits Get file →
IQ3_M2.0 GB 3.5 GB
Fits Get file →
Q2_K_L2.1 GB 3.6 GB
Fits Get file →
Q3_K_M2.1 GB 3.6 GB
Fits Get file →
Q3_K_L2.2 GB 3.7 GB
Fits Get file →
IQ4_XS2.3 GB 3.8 GB
Fits Get file →
Q4_02.4 GB 3.9 GB
Fits Get file →
Q4_K_S2.4 GB 3.9 GB
Fits Get file →
IQ4_NL2.4 GB 3.9 GB
Fits Get file →
Q4_K_M2.5 GB 4.0 GB
Fits Get file →
Q3_K_XL2.6 GB 4.1 GB
Fits Get file →
Q4_12.6 GB 4.1 GB
Fits Get file →
Q4_K_L2.8 GB 4.3 GB
Fits Get file →
Q5_K_S2.8 GB 4.3 GB
Fits Get file →
Q5_K_M2.9 GB 4.4 GB
Fits Get file →
Q5_K_L3.1 GB 4.6 GB
Fits Get file →
Q6_K3.3 GB 4.8 GB
Fits Get file →
Q6_K_L3.5 GB 5.0 GB
Fits Get file →
Q8_04.3 GB 5.8 GB
Fits Get file →
BF168.0 GB 9.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 2.38 GB, estimated 3.9 GB memory). For 12 GB VRAM, Q5_K_M (file size 2.87 GB, estimated 4.4 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (file size 3.3 GB, estimated 4.8 GB memory) provides a balance of quality and size.

What GPU do you need for Voxtral Mini 3B 2507?

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 (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.8 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 9.5 GB in use).

Which Voxtral Mini 3B 2507 quant should you choose?

Q4_K_M is the usual starting point for Voxtral Mini 3B 2507: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters4.01B
Layers30
Trained context131,072 tokens
KV cache (fp16)120 KB per token

Source

Quantized bybartowski
FamilyMistral
Licenseapache-2.0
Downloads (HF)4,484
Last updated2025-07-28

Frequently asked questions about Voxtral Mini 3B 2507

How much VRAM does Voxtral Mini 3B 2507 need?

About 4.0 GB at Q4_K_M with an 8K context window. That is the 2.5 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 3B 2507 on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Voxtral Mini 3B 2507 GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 1.6 GB, Q2_K is 1.7 GB, IQ3_XXS is 1.7 GB, IQ3_XS is 1.8 GB, Q3_K_S is 1.9 GB and 19 more.

What context length does Voxtral Mini 3B 2507 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.0 GB at 32K.

Where can I download Voxtral Mini 3B 2507 GGUF?

The files are on Hugging Face in the bartowski/mistralai_Voxtral-Mini-3B-2507-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 3B 2507 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 3B 2507 on 8 GB VRAM?

Yes, the Q4_0 quantization requires about 3.9 GB of VRAM at 8 k context, which fits within 8 GB.

Does the model support image input?

No, the model only supports audio and text input; vision capabilities are not included.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use with attribution.

Other GGUFs of Voxtral-Mini-3B-2507

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other small models

All small models →