Mistral AItransformer

Mistral Small (API)

22B parameters • 13.4GB VRAM (Q4 estimate) • 32,000 context

Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.

Specifications

Parameters

22B

VRAM (Q4 est.)

13.4 GB

VRAM (FP16)

44 GB

Context Window

32,000

Architecture

transformer

License

Mistral API TOS

Finding cloud alternatives...

Run Mistral Small (API) on Radeon RX 6800

~13.4GB VRAM needed at Q4. Radeon RX 6800 has 16GB — buy hardware or rent cloud.

Amazon eBay Compare cloud prices

We may earn a commission from cloud and hardware partners at no extra cost to you.

Find the cheapest GPU that can run Mistral Small (API)

Compatibility Lab — check every GPU × quantization combination

→

Run Mistral Small (API) on...

GB200 NVL72✅ Fits NVIDIA DGX H100✅ Fits AWS EC2 P5 Instance (8x H100)✅ Fits Azure ND H100 v5 (8x H100)✅ Fits Google Cloud A3 (8x H100)✅ Fits Lambda Labs 1-Click Cluster (8x H100)✅ Fits

VRAM Calculator→GPU Comparison→Cloud GPU Pricing→

← Back to Models

Mistral AItransformer

Mistral Small (API)

22B parameters • 13.4GB VRAM (Q4 estimate) • 32,000 context

Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.