🔌
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 AMD Radeon Pro W7900 48GB run GPT-2 Medium (FlashAttention)?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-2 Medium (FlashAttention) on the AMD Radeon Pro W7900 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 640k | 766.6-937 t/s | ~35.5-43.4 (slow) |
| Q8 | yes | 646k | 1533.3-1874 t/s | ~71-86.8 (slow) |
| Q4 | yes | 648k | 2738-3346.5 t/s | ~126.8-154.9 (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 AMD Radeon Pro W7900 48GB
→ GPT-2 Medium (FlashAttention) specs
→ Other hardware
FAQ
Can the AMD Radeon Pro W7900 48GB run GPT-2 Medium (FlashAttention)?▶
Yes. At Q4 it generates ~2738-3346.5 tok/s and fits up to 648k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~126.8-154.9 tok/s.
How much context fits?▶
At Q4, up to about 648k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.