🔌
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 Transformer (Adaptive Input Embeddings) WT103?
Yes — here's how fast and up to what context, with real measured numbers.
Transformer (Adaptive Input Embeddings) WT103 on the Intel Arc Pro B70
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 419k | 713.8-886.2 t/s | ~47-58.3 (slow) |
| Q8 | yes | 423k | 1427.7-1772.3 t/s | ~93.9-116.6 (slow) |
| Q4 | yes | 424k | 2549.5-3164.8 t/s | ~167.7-208.2 (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
→ Transformer (Adaptive Input Embeddings) WT103 specs
→ Other hardware
FAQ
Can the Intel Arc Pro B70 run Transformer (Adaptive Input Embeddings) WT103?▶
Yes. At Q4 it generates ~2549.5-3164.8 tok/s and fits up to 424k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~167.7-208.2 tok/s.
How much context fits?▶
At Q4, up to about 424k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.