New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Intel Gaudi 3 run CLIP (ResNet-50)?
Yes — here's how fast and up to what context, with real measured numbers.
CLIP (ResNet-50) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1771k | 12110.6-15033.9 t/s | ~130.9-162.5 (slow) |
| Q8 | yes | 1773k | 24221.2-30067.7 t/s | ~261.9-325.1 (slow) |
| Q4 | yes | 1773k | 43252.2-53692.4 t/s | ~467.6-580.5 (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 Intel Gaudi 3 run CLIP (ResNet-50)?▶
Yes. At Q4 it generates ~43252.2-53692.4 tok/s and fits up to 1773k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~467.6-580.5 tok/s.
How much context fits?▶
At Q4, up to about 1773k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.