🔌
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 GLM-2B?
Yes — here's how fast and up to what context, with real measured numbers.
GLM-2B on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2611k | 1460-1740 t/s | ~7.3-8.7 (slow) |
| Q8 | yes | 2642k | 2920-3480 t/s | ~14.6-17.4 (slow) |
| Q4 | yes | 2655k | 5214.3-6214.3 t/s | ~26.1-31.1 (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 GLM-2B?▶
Yes. At Q4 it generates ~5214.3-6214.3 tok/s and fits up to 2655k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~26.1-31.1 tok/s.
How much context fits?▶
At Q4, up to about 2655k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.