🔌
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 Arc Pro B60 run Llama Guard?
Yes — here's how fast and up to what context, with real measured numbers.
Llama Guard on the Intel Arc Pro B60
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 50k | 18.9-23.5 t/s | ~1.7-2.1 (slow) |
| Q8 | yes | 104k | 37.8-46.9 t/s | ~3.3-4.1 (slow) |
| Q4 | yes | 127k | 67.5-83.8 t/s | ~5.9-7.3 (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 Arc Pro B60 run Llama Guard?▶
Yes. At Q4 it generates ~67.5-83.8 tok/s and fits up to 127k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.9-7.3 tok/s.
How much context fits?▶
At Q4, up to about 127k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.