🔌
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 WizardLM-2 7B?
Yes — here's how fast and up to what context, with real measured numbers.
WizardLM-2 7B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 780k | 153.3-190.3 t/s | ~1.7-2.1 (slow) |
| Q8 | yes | 834k | 306.6-380.6 t/s | ~3.3-4.1 (slow) |
| Q4 | yes | 857k | 547.4-679.6 t/s | ~5.9-7.3 (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 WizardLM-2 7B?▶
Yes. At Q4 it generates ~547.4-679.6 tok/s and fits up to 857k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.9-7.3 tok/s.
How much context fits?▶
At Q4, up to about 857k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.