Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run Mistral Small 4 119B (MoE)?
Mistral · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Mistral Small 4 119B (MoE) at Q8_0 · 126.5 GB · 222–332 tok/s on a AMD Instinct MI300X (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 40.2 GB | 302–453 tok/s | Runs great |
| Q3_K_M | 54.4 GB | 285–428 tok/s | Runs great |
| Q4_K_M | 73.8 GB | 265–397 tok/s | Runs great |
| Q5_K_M | 89.2 GB | 250–376 tok/s | Runs great |
| Q6_K | 99.4 GB | 242–363 tok/s | Runs great |
| Q8_0 | 126.5 GB | 222–332 tok/s | Runs great |
| FP16 | 238.0 GB | 165–247 tok/s | Won't fit |
Open the full calculator →Everything a AMD Instinct MI300X (192GB) runsMistral Small 4 119B (MoE) on other machinesWhat to buy to run it →
Ran Mistral Small 4 119B (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →