Unverified50% confidenceBenchmarkExact time
Under a light load of 1,000 req/s, Bifrost's p50 is 0.72 ms and Antirion's is 0.76 ms, putting the two at similar performance.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
VerifiedWhen using FP16 precision, the KV Cache for LLaMA-2-7B occupies approximately 0.5 MB per token.61% similarUnverifiedRELAGRAM has only 0.53M parameters.61% similarUnverifiedqwen3.8 had a latency p50 of 18885ms and p95 of 42368ms, 15 to 20 times slower than Claude Sonnet 5's 1080ms median latency on the same task.60% 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.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062951API
curl https://kongchang.com/api/v1/knowledge/claims/1062951MCP
get_claim(id=1062951)