🔌
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 Vicuna-33B-v1.3?
Yes — here's how fast and up to what context, with real measured numbers.
Vicuna-33B-v1.3 on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 192k | 32.5-40.4 t/s | ~0.4-0.4 (slow) |
| Q8 | yes | 318k | 65-80.7 t/s | ~0.7-0.9 (slow) |
| Q4 | yes | 373k | 116.1-144.2 t/s | ~1.3-1.6 (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 Vicuna-33B-v1.3?▶
Yes. At Q4 it generates ~116.1-144.2 tok/s and fits up to 373k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.3-1.6 tok/s.
How much context fits?▶
At Q4, up to about 373k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.