🔌
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 1.6 Mini?
Yes — here's how fast and up to what context, with real measured numbers.
Jamba 1.6 Mini on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 37k | 20.6-25.6 t/s | ~0.2-0.3 (slow) |
| Q8 | yes | 196k | 41.3-51.2 t/s | ~0.4-0.6 (slow) |
| Q4 | yes | 266k | 73.7-91.5 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 1.6 Mini?▶
Yes. At Q4 it generates ~73.7-91.5 tok/s and fits up to 266k 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 266k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.