🔌
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 SciBERT?
Yes — here's how fast and up to what context, with real measured numbers.
SciBERT on the AMD Radeon Pro W7900 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 648k | 2474.2-3024 t/s | ~114.5-140 (slow) |
| Q8 | yes | 649k | 4948.4-6048 t/s | ~229.1-280 (slow) |
| Q4 | yes | 650k | 8836.4-10800 t/s | ~409.1-500 (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 AMD Radeon Pro W7900 48GB run SciBERT?▶
Yes. At Q4 it generates ~8836.4-10800 tok/s and fits up to 650k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~409.1-500 tok/s.
How much context fits?▶
At Q4, up to about 650k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.