🔌
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 Mixtral 8x7B?
Yes — here's how fast and up to what context, with real measured numbers.
Mixtral 8x7B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 70k | 23-28.5 t/s | ~0.2-0.3 (slow) |
| Q8 | yes | 212k | 46-57 t/s | ~0.5-0.6 (slow) |
| Q4 | yes | 275k | 82.1-101.9 t/s | ~0.9-1.1 (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 Mixtral 8x7B?▶
Yes. At Q4 it generates ~82.1-101.9 tok/s and fits up to 275k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.9-1.1 tok/s.
How much context fits?▶
At Q4, up to about 275k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.