🔌
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 DeepSeek-R1-Distill-Qwen-1.5B?
Yes — here's how fast and up to what context, with real measured numbers.
DeepSeek-R1-Distill-Qwen-1.5B on the AMD Radeon Pro W7900 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 597k | 152.9-186.9 t/s | ~7.1-8.7 (slow) |
| Q8 | yes | 624k | 305.8-373.8 t/s | ~14.2-17.3 (slow) |
| Q4 | yes | 636k | 546.1-667.4 t/s | ~25.3-30.9 (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
→ DeepSeek-R1-Distill-Qwen-1.5B specs
→ Other hardware
FAQ
Can the AMD Radeon Pro W7900 48GB run DeepSeek-R1-Distill-Qwen-1.5B?▶
Yes. At Q4 it generates ~546.1-667.4 tok/s and fits up to 636k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~25.3-30.9 tok/s.
How much context fits?▶
At Q4, up to about 636k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.