🔌
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 NVIDIA B200 run Qwen2.5-Coder (1.5B)?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen2.5-Coder (1.5B) on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2625k | 1896.1-2259.7 t/s | ~9.5-11.3 (slow) |
| Q8 | yes | 2649k | 3792.2-4519.5 t/s | ~19-22.6 (slow) |
| Q4 | yes | 2659k | 6771.8-8070.5 t/s | ~33.9-40.4 (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 NVIDIA B200 run Qwen2.5-Coder (1.5B)?▶
Yes. At Q4 it generates ~6771.8-8070.5 tok/s and fits up to 2659k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~33.9-40.4 tok/s.
How much context fits?▶
At Q4, up to about 2659k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.