🔌
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 Intel Gaudi 3 run Codestral?
Yes — here's how fast and up to what context, with real measured numbers.
Codestral on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 274k | 48.3-60 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 359k | 96.7-120 t/s | ~1-1.3 (slow) |
| Q4 | yes | 396k | 172.6-214.3 t/s | ~1.9-2.3 (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 Intel Gaudi 3 run Codestral?▶
Yes. At Q4 it generates ~172.6-214.3 tok/s and fits up to 396k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.9-2.3 tok/s.
How much context fits?▶
At Q4, up to about 396k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.