CanItRun Logocanitrun.

Mistral Small 22B

Mistral Small 22B needs roughly 16.1 GB VRAM at Q4_K_M quantization (51.8 GB at FP16). 91 GPUs we track can run it fully in VRAM at 8k context.

91 GPUs run this natively · 13 with CPU offload

Mistral AI22.2B params32k contextMistral ResearchNon-commercial only

Mistral Small 22B is a 22.2B parameter dense model developed by Mistral AI. September 2024 22B model with strong general capabilities.

To run Mistral Small 22B locally: Q4_K_M ~14-15GB — fits on 16GB GPUs. Good 16GB GPU choice.

MMLU-Pro 49.2%, HumanEval 81.1% — solid mid-range performer.

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP3288.8 GB1.88 GB101.6 GB
BF1644.4 GB1.88 GB51.8 GB
FP1644.4 GB1.88 GB51.8 GB
Q8_022.2 GB1.88 GB27.0 GB
Q6_K18.2 GB1.88 GB22.5 GB
Q5_K_M14.3 GB1.88 GB18.1 GB
Q4_K_Mrec12.5 GB1.88 GB16.1 GB
Q3_K_M9.6 GB1.88 GB12.8 GB
Q2_K7.3 GB1.88 GB10.3 GB
NVFP4cuda11.1 GB1.88 GB14.5 GB

KV cache shown at 8k context (FP16). NVFP4 requires a CUDA GPU. Enable TurboQuant in the calculator to see reduced KV cache estimates.

Benchmarks

MMLU-Pro
49.2
GPQA Diamond
44
IFEval
72.8
MATH
70

GPUs that run Mistral Small 22B natively (91)

Plus 13 GPUs that run it with CPU offload (slower)
Hugging Face ↗Ollama ↗Released 2024-09-18

Frequently asked questions

What are the VRAM requirements for Mistral Small 22B?
Mistral Small 22B requires approximately 16.1 GB of VRAM at Q4_K_M quantization, 27.0 GB at Q8, and 51.8 GB at FP16. These numbers assume 8k context window; VRAM scales linearly with context length due to the KV cache.
How many parameters does Mistral Small 22B have?
Mistral Small 22B has 22.2 billion parameters.
How capable is Mistral Small 22B?
Mistral Small 22B has an MMLU-Pro score of 49.2, making it well-suited for lightweight tasks, prototyping, and resource-constrained environments.
Can Mistral Small 22B run on a 16 GB GPU?
No. At Q4_K_M, Mistral Small 22B needs 16.1 GB of VRAM — more than 16 GB. You will need a 24 GB GPU like the RTX 4090 or RTX 3090.
Can Mistral Small 22B run on a 24 GB GPU?
Yes. Mistral Small 22B fits in a 24 GB GPU at Q4_K_M, requiring 16.1 GB VRAM. GPUs with 24 GB include the RTX 4090, RTX 3090, and RTX 3090 Ti.
What is the smallest quantization for Mistral Small 22B that fits in 24 GB of VRAM?
At NVFP4, Mistral Small 22B needs 14.5 GB — the highest-quality quantization that fits in 24 GB of VRAM.
What GPU do I need to run Mistral Small 22B locally?
A 24 GB GPU is the minimum. At Q4_K_M, Mistral Small 22B needs 16.1 GB VRAM. Good options: RTX 4090 (24 GB), RTX 3090 (24 GB).