Mistral GGUF models

9355 GGUF models in the Mistral family, quantized by 2133 uploaders. Sizes run from 2M to 1050B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MI
Voxtral Mini 4B Realtime
Mistral · handy-computer
Params4.43B
Context—
Q4_K_M2.8 GB
GGUF
MI
Voxtral Small 24B
Mistral · handy-computer
Params24.3B
Context—
Q4_K_M14.3 GB
GGUF
MI
Cydonia 24B v4.3
Mistral · TheDrummer
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
MI
Devstral-Small-2-24B-Instruct-2512
Mistral · unsloth
Params23.6B
Context384K
Q4_K_M14.3 GB
CodingVision
MI
Hermes 2 Pro Mistral 7B
Mistral · NousResearch
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Mistral-Small-3.2-24B-Instruct-2506
Mistral · unsloth
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
MI
models--mistralai--Mistral-7B-Instruct-v0.3
Mistral · MaziyarPanahi
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Ministral 3 3B Instruct 2512
Mistral · mistralai
Params3.43B
Context256K
Q4_K_M2.1 GB
Vision
MI
models--v2ray--Mixtral-8x22B-v0.1
Mistral · MaziyarPanahi
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
MI
Ministral 3 8B Instruct 2512
Mistral · mistralai
Params8.49B
Context256K
Q4_K_M5.2 GB
Vision
MI
Mistral Small 3.2 24B Instruct 2506
Mistral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
MI
mistralai_mistral-7b-instruct-v0.2
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Models Mistralai Ministral 3 3B Reasoning 2512
Mistral · MaziyarPanahi
Params3.43B
Context256K
Q4_K_M2.1 GB
Reasoning
MI
mistralai_Devstral Small 2 24B Instruct 2512
Mistral · lmstudio-community
Params23.6B
Context384K
Q4_K_M14.3 GB
CodingVision
MI
Models Mrfakename Mistral Small 3.1 24b Instruct 2503 Hf
Mistral · MaziyarPanahi
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
MI
Models Mistralai Mistral Nemo Instruct 2407
Mistral · MaziyarPanahi
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mistral-7B-Instruct-v0.3
Mistral · thesven
Params7B
Context32K
Q4_K_M4.4 GB
GGUF
MI
models--mistralai--mathstral-7B-v0.1
Mistral · MaziyarPanahi
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Rocinante X 12B v1
Mistral · TheDrummer
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
MI
Models Mistralai Mistral Small Instruct 2409
Mistral · MaziyarPanahi
Params22.2B
Context32K
Q4_K_M13.3 GB
GGUF
MI
Models Mistralai Mistral Small 24B Instruct 2501
Mistral · MaziyarPanahi
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
MI
Models Mistralai Mistral Large Instruct 2411
Mistral · MaziyarPanahi
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
MI
Ministral 3 14B Instruct 2512
Mistral · mistralai
Params13.5B
Context256K
Q4_K_M8.2 GB
Vision
MI
Mistral-7B-Instruct-v0.3
Mistral · bartowski
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
MI
mistralai_mistral-7b-instruct-v0.1
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Dolphin Mistral 24B Venice Edition
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
MI
Voxtral Mini 3B
Mistral · handy-computer
Params4.7B
Context—
Q4_K_M3.0 GB
GGUF
MI
Dolphin3.0 Mistral 24B
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
CodingTool use
MI
Ministral-3-3B-Instruct-2512
Mistral · unsloth
Params3.43B
Context256K
Q4_K_M2.1 GB
Vision

About the Mistral GGUF models

Mistral is represented on ggufmodels.com by 9,355 GGUF models, quantized by 2,133 uploaders on Hugging Face. The most downloaded are Voxtral Mini 4B Realtime, Voxtral Small 24B and Cydonia 24B v4.3. Parameter counts run from 2M to 1050B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Mistral model is between 0.0 to 411.4 GB, which is the quant most people start with. Most files come from mradermacher (2690), RichardErkhov (1031) and MaziyarPanahi (414). The quants you will meet most often are Q4_K_M (6915), Q5_K_M (5803), Q2_K (5665) and Q6_K (5580), where the number is how many models offer that quant.

Frequently asked questions

Which Mistral GGUF should I download?

The most downloaded Mistral GGUF here is Voxtral Mini 4B Realtime. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Mistral model need?

Q4_K_M files of Mistral models on this site range from 0.0 to 411.4 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Mistral GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and MaziyarPanahi. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing