🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Instinct MI430X run Codestral?
Yes — here's how fast and up to what context, with real measured numbers.
Codestral on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1341k | 330.6-404.1 t/s | ~0.6-0.7 (slow) |
| Q8 | yes | 1426k | 661.2-808.2 t/s | ~1.1-1.4 (slow) |
| Q4 | yes | 1463k | 1180.7-1443.1 t/s | ~2-2.5 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the Instinct MI430X run Codestral?▶
Yes. At Q4 it generates ~1180.7-1443.1 tok/s and fits up to 1463k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2-2.5 tok/s.
How much context fits?▶
At Q4, up to about 1463k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.