MI

Mistral-Small-24B-Base-2501

MistralGGUF by ddh0Updated 2025-01-30
Download on Hugging Face
Parameters23.6B
Context32K
Layers40
Architecturellama
Smallest quant14.0 GB
Quick answer

Mistral-Small-24B-Base-2501 needs about 15.9 GB of memory at Q8_0 (a 14.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 14.0 GB (Q8_0) to 19.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Mistral-Small-24B-Base-2501 is a 23.6B-parameter Mistral model in GGUF format, quantized by ddh0. Its trained context length is 32K tokens. The repository has 2 quant files, from 14.0 GB (Q8_0) to 19.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_014.0 GB 15.9 GB
Too big Get file →
Q8_019.7 GB 21.5 GB
Too big Get file →

What GPU do you need for Mistral-Small-24B-Base-2501?

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: the best quant that fits is Q8_0 (14.0 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (19.7 GB file, about 21.5 GB in use).

Which Mistral-Small-24B-Base-2501 quant should you choose?

Q8_0 (14.0 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 context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byddh0
FamilyMistral
Licenseapache-2.0
Downloads (HF)13
Last updated2025-01-30

Frequently asked questions about Mistral-Small-24B-Base-2501

How much VRAM does Mistral-Small-24B-Base-2501 need?

About 15.9 GB at Q8_0 with an 8K context window. That is the 14.0 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 Mistral-Small-24B-Base-2501 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral-Small-24B-Base-2501 GGUF?

It depends on the quant: Q8_0 is 14.0 GB, Q8_0 is 19.7 GB.

What context length does Mistral-Small-24B-Base-2501 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Mistral-Small-24B-Base-2501 GGUF?

The files are on Hugging Face in the ddh0/Mistral-Small-24B-Base-2501-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 Mistral-Small-24B-Base-2501 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 Mistral-Small-24B-Base-2501

Similar models

Browse all →

More from ddh0

All by ddh0 →

More Mistral models

All Mistral →

Other medium models

All medium models →