🔌
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 Qwen3-GNR-it 14B?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen3-GNR-it 14B on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 898k | 208.6-248.6 t/s | ~1-1.2 (slow) |
| Q8 | yes | 984k | 417.1-497.1 t/s | ~2.1-2.5 (slow) |
| Q4 | yes | 1021k | 744.9-887.8 t/s | ~3.7-4.4 (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 Qwen3-GNR-it 14B?▶
Yes. At Q4 it generates ~744.9-887.8 tok/s and fits up to 1021k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.7-4.4 tok/s.
How much context fits?▶
At Q4, up to about 1021k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.