🔌
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 Jamba?
Yes — here's how fast and up to what context, with real measured numbers.
Jamba on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 40k | 20.8-25.8 t/s | ~0.2-0.3 (slow) |
| Q8 | yes | 197k | 41.6-51.6 t/s | ~0.4-0.6 (slow) |
| Q4 | yes | 267k | 74.3-92.2 t/s | ~0.8-1 (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 Jamba?▶
Yes. At Q4 it generates ~74.3-92.2 tok/s and fits up to 267k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.8-1 tok/s.
How much context fits?▶
At Q4, up to about 267k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.