🔌
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 B70 run DEQ-Transformer (Post-LN) + Jacobian Regularisation?
Yes — here's how fast and up to what context, with real measured numbers.
DEQ-Transformer (Post-LN) + Jacobian Regularisation on the Intel Arc Pro B70
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 423k | 1799.2-2233.5 t/s | ~118.4-146.9 (slow) |
| Q8 | yes | 425k | 3598.4-4466.9 t/s | ~236.7-293.9 (slow) |
| Q4 | yes | 425k | 6425.7-7976.7 t/s | ~422.7-524.8 (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.
→ All models on the Intel Arc Pro B70
→ DEQ-Transformer (Post-LN) + Jacobian Regularisation specs
→ Other hardware
FAQ
Can the Intel Arc Pro B70 run DEQ-Transformer (Post-LN) + Jacobian Regularisation?▶
Yes. At Q4 it generates ~6425.7-7976.7 tok/s and fits up to 425k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~422.7-524.8 tok/s.
How much context fits?▶
At Q4, up to about 425k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.