🔌
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 H200 run TeleChat2-35B?
Yes — here's how fast and up to what context, with real measured numbers.
TeleChat2-35B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 222k | 50.1-59.7 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 356k | 100.1-119.3 t/s | ~0.8-1 (slow) |
| Q4 | yes | 414k | 178.8-213.1 t/s | ~1.5-1.8 (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 TeleChat2-35B?▶
Yes. At Q4 it generates ~178.8-213.1 tok/s and fits up to 414k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.5-1.8 tok/s.
How much context fits?▶
At Q4, up to about 414k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.