GPU rankings
GLM 5.3 744B

Cheapest GPU for GLM-5.2

Measured on the AgentX agentic coding workload at a matched interactivity target of 50 tokens/s per user. Hardware without a measurement at this operating point is not ranked.

Cheapest GPU for GLM-5.2: live benchmark ranking
RankGPUTokens/s per GPU$ / 1M tokensPrecisionEngine
1MI355X10,382$0.040fp4SGLang

Optimizing for speed instead of cost? See the fastest GPU for GLM-5.2

Methodology

Every number on this page is a measurement, not a spec-sheet estimate. The InferenceX fleet serves GLM-5.2 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 cheapest GPU to run GLM-5.2?
As of the latest benchmark runs, MI355X is cheapest at $0.040 per million total tokens on the AgentX agentic coding workload, at hyperscaler $/GPU/hr pricing and a matched interactivity target of 50 tokens/s per user.
How is cost per million tokens calculated?
Measured throughput per GPU at the 50 tokens/s per user tier is converted to $ per million total (input plus output) tokens using hyperscaler $/GPU/hr rates from the SemiAnalysis AI Cloud TCO model. Slower interactivity targets or cheaper rental tiers change the absolute numbers but rarely the order.
How often is this ranking updated?
Benchmarks re-run continuously on the InferenceX cluster fleet; the newest result feeding this ranking landed on 2026-08-25. The page always renders the latest data.

Explore the data