🔌
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 DeciLM 6B?
Yes — here's how fast and up to what context, with real measured numbers.
DeciLM 6B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 800k | 188.2-233.7 t/s | ~2-2.5 (slow) |
| Q8 | yes | 844k | 376.5-467.4 t/s | ~4.1-5.1 (slow) |
| Q4 | yes | 863k | 672.3-834.6 t/s | ~7.3-9 (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 DeciLM 6B?▶
Yes. At Q4 it generates ~672.3-834.6 tok/s and fits up to 863k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.3-9 tok/s.
How much context fits?▶
At Q4, up to about 863k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.