🔌
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 CausalLM 34B β?
Yes — here's how fast and up to what context, with real measured numbers.
CausalLM 34B β on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 181k | 31.2-38.7 t/s | ~0.3-0.4 (slow) |
| Q8 | yes | 312k | 62.4-77.4 t/s | ~0.7-0.8 (slow) |
| Q4 | yes | 370k | 111.4-138.3 t/s | ~1.2-1.5 (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 CausalLM 34B β?▶
Yes. At Q4 it generates ~111.4-138.3 tok/s and fits up to 370k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.2-1.5 tok/s.
How much context fits?▶
At Q4, up to about 370k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.