🔌
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 ImageBind?
Yes — here's how fast and up to what context, with real measured numbers.
ImageBind on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1746k | 1151.3-1429.2 t/s | ~12.4-15.5 (slow) |
| Q8 | yes | 1760k | 2302.6-2858.4 t/s | ~24.9-30.9 (slow) |
| Q4 | yes | 1766k | 4111.7-5104.2 t/s | ~44.5-55.2 (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 ImageBind?▶
Yes. At Q4 it generates ~4111.7-5104.2 tok/s and fits up to 1766k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~44.5-55.2 tok/s.
How much context fits?▶
At Q4, up to about 1766k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.