🔌
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 minChatGPT?
Yes — here's how fast and up to what context, with real measured numbers.
minChatGPT on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1724k | 654.7-812.7 t/s | ~7.1-8.8 (slow) |
| Q8 | yes | 1749k | 1309.3-1625.4 t/s | ~14.2-17.6 (slow) |
| Q4 | yes | 1760k | 2338.1-2902.5 t/s | ~25.3-31.4 (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 minChatGPT?▶
Yes. At Q4 it generates ~2338.1-2902.5 tok/s and fits up to 1760k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~25.3-31.4 tok/s.
How much context fits?▶
At Q4, up to about 1760k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.