GPU rankings
GLM 5/5.1

Fastest GPU for GLM-5

B300 leads at 2,988 tokens/s per GPU, 7% ahead of B200.

Measured on a single-turn chat workload (8k input / 1k output) at a matched interactivity target of 50 tokens/s per user. Hardware without a measurement at this operating point is not ranked.

Fastest GPU for GLM-5: live benchmark ranking
RankGPUTokens/s per GPU$ / 1M tokensPrecisionEngine
1B3002,988$0.21fp4SGLang
2B2002,792$0.17fp4SGLang
3GB200 NVL721,553$0.33fp4Dynamo SGLang
4GB300 NVL721,482$0.43fp4Dynamo SGLang
5MI355X967$0.43fp8SGLang

Optimizing for cost instead of speed? See the cheapest GPU for GLM-5

Methodology

Every number on this page is a measurement, not a spec-sheet estimate. The InferenceX fleet serves GLM-5 on real hardware with community serving engines, sweeping concurrency to trace each platform's throughput-versus-interactivity frontier.

Platforms are then read at the same operating point (50 tokens/s per user) so the comparison is iso-interactivity: a GPU cannot win by quoting throughput at an unusably slow per-user speed. Cost converts measured throughput to $ per million total tokens using $/GPU/hr rates from the SemiAnalysis AI Cloud TCO model.

The derivation is shared with the InferenceX overview leaderboard, and results re-run continuously, so this ranking updates as new engine releases and configs land.

Frequently asked questions

What is the fastest GPU for GLM-5 inference?
As of the latest benchmark runs, B300 leads at 2,988 tokens/s per GPU on a single-turn chat workload (8k input / 1k output), measured at a matched interactivity target of 50 tokens/s per user.
How is "fastest" measured?
Every platform is read at the same interactivity tier (50 tokens/s per user) on a single-turn chat workload (8k input / 1k output), then ranked by measured throughput per GPU. This is the same derivation the InferenceX overview leaderboard renders, so the ranking can never disagree with the dashboard.
How often is this ranking updated?
Benchmarks re-run continuously on the InferenceX cluster fleet; the newest result feeding this ranking landed on 2026-08-24. The page always renders the latest data.

Explore the data