New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the NVIDIA H200 run Segatron XL base, M=384?
Yes — here's how fast and up to what context, with real measured numbers.
Segatron XL base, M=384 on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1949k | 6817.1-8124.5 t/s | ~56.8-67.7 (slow) |
| Q8 | yes | 1953k | 13634.2-16249 t/s | ~113.6-135.4 (slow) |
| Q4 | yes | 1954k | 24346.9-29016.1 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 H200 run Segatron XL base, M=384?▶
Yes. At Q4 it generates ~24346.9-29016.1 tok/s and fits up to 1954k 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 1954k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.