Expired50% confidenceBenchmarkExact time
The AMD MI355X running GLM5.2 achieved an inference throughput of 2626 tokens/second on a single node.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/7/2026
First Seen
Valid until: 10/5/2026(expired)
Sources
AMD MI355X运行GLM5.2：推理成本仅为英伟达Blackwell的一半
hackernewshackernews7/3/2026
Related Claims
UnverifiedAMD MI355X 的性能对比结果已在 SemiAnalysis 的 InferenceX 仪表板上公开展示69% similarUnverifiedAMD MI355X在硬件层面原生支持FP8计算，这是其相比上一代MI300X的重要能力升级68% similarUnverifiedAMD Instinct MI355X 在 DeepSeek-R1 分离式推理的总拥有成本（TCO）上比 NVIDIA B200 TRT-LLM 低 5%67% similarUnverifiedThe AMD R7-H255 is manufactured using TSMC's 4nm process.63% similarUnverifiedThe MI355X belongs to AMD's Instinct series of data center accelerator cards and is evolved from the CDNA architecture.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/186795API
curl https://kongchang.com/api/v1/knowledge/claims/186795MCP
get_claim(id=186795)