🔌
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 HuatuoGPT?
Yes — here's how fast and up to what context, with real measured numbers.
HuatuoGPT on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 551k | 82.5-102.5 t/s | ~0.9-1.1 (slow) |
| Q8 | yes | 630k | 165.1-204.9 t/s | ~1.8-2.2 (slow) |
| Q4 | yes | 665k | 294.8-365.9 t/s | ~3.2-4 (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 HuatuoGPT?▶
Yes. At Q4 it generates ~294.8-365.9 tok/s and fits up to 665k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.2-4 tok/s.
How much context fits?▶
At Q4, up to about 665k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.