🔌
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 Tongyi DeepResearch?
Yes — here's how fast and up to what context, with real measured numbers.
Tongyi DeepResearch on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 211k | 35.2-43.7 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 327k | 70.4-87.3 t/s | ~0.8-0.9 (slow) |
| Q4 | yes | 378k | 125.6-156 t/s | ~1.4-1.7 (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 Tongyi DeepResearch?▶
Yes. At Q4 it generates ~125.6-156 tok/s and fits up to 378k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.4-1.7 tok/s.
How much context fits?▶
At Q4, up to about 378k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.