MI

MaVistral

MistralGGUF by amine-khelifUpdated 2025-07-07
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant25.1 GB
Quick answer

MaVistral needs about 26.9 GB of memory at Q8_0 (a 25.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 25.1 GB (Q8_0) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

MaVistral is a 23.6B-parameter Mistral model in GGUF format, quantized by amine-khelif. Its trained context length is 128K tokens. The repository has 2 quant files, from 25.1 GB (Q8_0) to 47.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_025.1 GB 26.9 GB
Too big Get file →
BF1647.2 GB 49.0 GB
Too big Get file →

What GPU do you need for MaVistral?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).

Which MaVistral quant should you choose?

Q8_0 (25.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byamine-khelif
FamilyMistral
Licenseapache-2.0
Downloads (HF)61
Last updated2025-07-07

Frequently asked questions about MaVistral

How much VRAM does MaVistral need?

About 26.9 GB at Q8_0 with an 8K context window. That is the 25.1 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 MaVistral on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MaVistral GGUF?

It depends on the quant: Q8_0 is 25.1 GB, BF16 is 47.2 GB.

What context length does MaVistral support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download MaVistral GGUF?

The files are on Hugging Face in the amine-khelif/MaVistral-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 MaVistral 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.

Other GGUFs of Magistral-Small-2506

Similar models

Browse all →

More from amine-khelif

All by amine-khelif →

More Mistral models

All Mistral →

Other medium models

All medium models →