Coding with AI / 8x B200
8x B200
Memory: 1536 GB.
Memory bandwidth: 64000 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: 120 tok/s (estimate: bandwidth-bound approximation (scaled from 8x H200 measured 75 tok/s single stream, aggregate 38.4 -> 61.6 TB/s; vendor 540 c Π°Π³ΡΠ΅ΡΡΠΈΠ²Π½ΡΠΌ EAGLE ΠΎΡΠ²Π΅ΡΠ³Π½ΡΡ ΠΊΠ°ΠΊ spec-decode))
- 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 B200 (1536 GB) at its release date, by SWE-bench Verified.
- 2025-07-22 Qwen3-Coder-480B 69.6%
- 2025-11-06 Kimi K2 Thinking 71.3%
- 2025-12-09 Devstral 2 72.2%
- 2025-12-22 GLM-4.7 73.8%