The cheapest cataloged machine that runs Mistral Small 3 on the GPU is a AMD Radeon RX 6800 XT · 16GB VRAM. Here are the most affordable rigs that fit it, smallest memory first.
| machine | best fit | verdict | speed |
|---|---|---|---|
| AMD Radeon RX 6800 XT · 16GB VRAM | 24B Q3_K_M | ✅ Runs (tight) | 16–25 tok/s |
| AMD Radeon RX 6950 XT · 16GB VRAM | 24B Q3_K_M | ✅ Runs (tight) | 18–30 tok/s |
| AMD Radeon RX 7800 XT · 16GB VRAM | 24B Q3_K_M | ✅ Runs (tight) | 19–30 tok/s |
| NVIDIA GeForce RTX 4080 · 16GB VRAM | 24B Q3_K_M | ✅ Runs (tight) | 25–40 tok/s |
| NVIDIA GeForce RTX 5080 · 16GB VRAM | 24B Q3_K_M | ✅ Runs (tight) | 30–50 tok/s |
| AMD Radeon RX 7900 XT · 20GB VRAM | 24B Q5_K_M | ✅ Runs (tight) | 17–30 tok/s |
| AMD Radeon RX 7900 XTX · 24GB VRAM | 24B Q5_K_M | ✅ Runs (tight) | 20–35 tok/s |
| Apple M2 · 24GB | 24B Q3_K_M | ✅ Runs (tight) | 5–8 tok/s |
| Apple M4 · 24GB | 24B Q3_K_M | ✅ Runs (tight) | 5–9 tok/s |
| Apple M4 Pro · 24GB | 24B Q3_K_M | ✅ Runs (tight) | 11–18 tok/s |
| NVIDIA GeForce RTX 3090 · 24GB VRAM | 24B Q5_K_M | ✅ Runs (tight) | 20–35 tok/s |
| NVIDIA GeForce RTX 4090 · 24GB VRAM | 24B Q5_K_M | ✅ Runs (tight) | 25–40 tok/s |
Already have a machine? See Mistral Small 3 across popular rigs → or check your exact rig →
Planning a whole workflow? Rigs for a coding agent · local chat · reasoning · local RAG setup.
Verdicts use the same GQA-aware fit math as the CLI — a AMD Radeon RX 6800 XT verdict here matches what runlocal tells you on the machine.