GLM 5/5.1 — B300 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on GLM 5/5.1. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
B300 / GB300 NVL72 on GLM 5/5.1 at 47 tok/s/user: 1959 / 1202 tok/s/GPU, $0.33 / $0.61 per million tokens. B300 is 89% cheaper per token; B300 delivers 63% more tok/s/GPU.
Around the middle of the 33–88 tok/s/user interactivity band, at 61 tok/s/user on GLM 5/5.1: B300 runs 1556 tok/s/GPU at $0.42/M tokens, GB300 NVL72 runs 381 at $1.93/M. B300 is 361% cheaper per token; B300 delivers 308% more tok/s/GPU.
Setting 75 tok/s/user as the target on GLM 5/5.1, B300 produces 1153 tok/s/GPU ($0.56 per million tokens) and GB300 NVL72 produces 135 ($5.45). B300 is 867% cheaper per token; B300 delivers 755% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B300:1959.4GB300 NVL72:1201.8 | B300:1556.2GB300 NVL72:381.5 | B300:1153.3GB300 NVL72:135.0 |
| Cost ($/M tok) | B300:$0.326GB300 NVL72:$0.614 | B300:$0.419GB300 NVL72:$1.931 | B300:$0.564GB300 NVL72:$5.452 |
| tok/s/MW | B300:902937GB300 NVL72:572265 | B300:717134GB300 NVL72:181649 | B300:531465GB300 NVL72:64268 |
| Concurrency | B300:~85GB300 NVL72:~513 | B300:~52GB300 NVL72:~258 | B300:~32GB300 NVL72:~70 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.