Unverified50% confidenceBenchmarkExact time
As a draft model for Qwen3-32B, SHADOW boosted llama.cpp generation speed from 19.7 to 28.5 tok/s through speculative decoding.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe RTX 4090 has a theoretical FP16 compute performance of 330 TFLOPS, and the actual Decode speed for a 7B FP16 model is typically 50–60 tokens/s.69% similarVerifiedIn benchmark testing, Qwen3 27B achieved a generation speed of approximately 40-something tokens per second on 4 modified 2080 Ti cards without NVLink enabled.67% similarUnverifiedCSRT追踪器由Lukezic等人于CVPR 2017提出，速度约为25fps64% similarVerifiedQwen2.5-Coder-32B running with Q4 quantization on an RTX 4090 can achieve an inference speed of 40–60 tokens per second.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/922681API
curl https://kongchang.com/api/v1/knowledge/claims/922681MCP
get_claim(id=922681)