Unverified50% confidenceBenchmarkExact time
AntAngelMed achieves inference speeds of over 200 tokens/s on H20 hardware.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
Valid until: 10/28/2026
Sources
Related Entities
Related Claims
Unverified测试者用双4090（48GB显存）工作站运行20.7B稠密模型，每秒生成27.6个Token，仅比矮星略快，但参数量小10倍以上68% similarUnverifiedOfficial estimates suggest a 24GB GPU can run approximately 100–140 tokens/second.66% similarUnverifiedIf bandwidth reached 2.4 TB/s, the theoretical speed ceiling for a 100 GB model could reach 24 tokens/s, a 60 GB model 40 tokens/s, and a 35 GB model close to 69 tokens/s.66% similarUnverifiedIn benchmark testing on an AMD RX 7900 GPU, Ornith 35B achieved an overall accuracy of 85% (18 out of 21 passed), a generation speed of 74 tokens/s, a prompt processing speed of 850 tokens/s, and a VRAM usage of 20 GB.66% similarUnverifiedIn tests with the 4-bit quantized version (fitting entirely into 32 GB of VRAM), Ollama reached 240 tokens/s while FreeToken reached 225 tokens/s, making Ollama actually faster.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032155API
curl https://kongchang.com/api/v1/knowledge/claims/1032155MCP
get_claim(id=1032155)