Unverified50% confidenceBenchmarkExact time
Under the same benchmark conditions, the per-GPU throughput of the 8-GPU AMD MI355X is 24.4% higher than the 6,083 tok/s/GPU of the HGX B300.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedIn SemiAnalysis's AgentX benchmark, an 8-GPU AMD MI355X achieved 7,567 tok/s per GPU in Kimi K3 model serving at an interactive latency of 50 tok/s/user.73% similarUnverifiedIn a prefill-only test running gpt-oss-120b on 4× B200s, DWDP4 achieves a 1.92× speedup over DEP4 under the MNT 32K/ISL 32K configuration and a 1.54× throughput improvement at saturation (506K vs. 329K tok/s).73% similarUnverifiedThe NVIDIA A100's theoretical FP16 peak compute is approximately 312 TFLOPS, but GPU utilization in naive LLM inference scenarios is often below 30%.70% similarUnverifiedThe most advanced HBM3e memory bandwidth is approximately 4.8 TB/s, yet GPU compute utilization during inference often reaches only 30%–60%.69% similarUnverifiedAt FP16 half-precision computation, the RTX 4090 has a theoretical performance of approximately 330 TFLOPS, while the M2 Ultra's GPU delivers approximately 27.2 TFLOPS.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1050930API
curl https://kongchang.com/api/v1/knowledge/claims/1050930MCP
get_claim(id=1050930)