New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the NVIDIA B200 run Transformer-XL (257M)?
Yes — here's how fast and up to what context, with real measured numbers.
Transformer-XL (257M) on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2665k | 11361.9-13540.9 t/s | ~56.8-67.7 (slow) |
| Q8 | yes | 2669k | 22723.7-27081.7 t/s | ~113.6-135.4 (slow) |
| Q4 | yes | 2670k | 40578.1-48360.2 t/s | ~202.9-241.8 (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 Transformer-XL (257M)?▶
Yes. At Q4 it generates ~40578.1-48360.2 tok/s and fits up to 2670k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~202.9-241.8 tok/s.
How much context fits?▶
At Q4, up to about 2670k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.