can-i-run-this-llm

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 · 221–331 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M54.4 GB284–425 tok/sRuns great
Q4_K_M73.8 GB263–395 tok/sRuns great
Q5_K_M89.2 GB249–374 tok/sRuns great
Q6_K99.4 GB241–361 tok/sRuns great
Q8_0126.5 GB221–331 tok/sRuns great
FP16238.0 GB164–246 tok/sWon't fit

Ran Mistral Small 4 119B (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →