🔌
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 Stable Code 3B?
Yes — here's how fast and up to what context, with real measured numbers.
Stable Code 3B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1689k | 383.7-476.3 t/s | ~4.1-5.1 (slow) |
| Q8 | yes | 1731k | 767.4-952.6 t/s | ~8.3-10.3 (slow) |
| Q4 | yes | 1750k | 1370.4-1701.1 t/s | ~14.8-18.4 (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 Stable Code 3B?▶
Yes. At Q4 it generates ~1370.4-1701.1 tok/s and fits up to 1750k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~14.8-18.4 tok/s.
How much context fits?▶
At Q4, up to about 1750k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.