Coding with AI / 8x H200

8x H200

Memory: 1128 GB. Memory bandwidth: 38400 GB/s. Generation speed is bound by the chip's bandwidth; memory decides which models fit.

How to run

GLM-5.2 smart

• Score: 82.7% (Terminal-Bench 2), source
• Speed: 75 tok/s (measured, source)
• Conditions: engine SGLang, quant W4AFP8, context 128
• Min memory: 512 GB
• Command: glm-5.2-W4AFP8.gguf

Every number above is either a measurement with a source or a labeled estimate with a method. Unlabeled estimates do not exist on this site.

Ceiling timeline

The strongest model fitting 8x H200 (1128 GB) at its release date, by SWE-bench Verified.

1. 2025-07-22 Qwen3-Coder-480B 69.6%
2. 2025-11-06 Kimi K2 Thinking 71.3%
3. 2025-12-09 Devstral 2 72.2%
4. 2025-12-22 GLM-4.7 73.8%