Unverified50% confidenceBenchmarkExact time
The RTX 3090 cannot run the NVFP4 quantization format because its Ampere architecture Tensor Cores do not support NVFP4 instructions, leaving only the Q4 format available, with speeds of 40–48 tokens/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/3/2026
First Seen
Valid until: 12/2/2026
Sources
Related Entities
Related Claims
UnverifiedIn benchmark testing, Qwen3 27B achieved a generation speed of approximately 40-something tokens per second on 4 modified 2080 Ti cards without NVLink enabled.68% similarUnverifiedThe RTX 4060 can achieve generation speeds 3-5 times that of the GTX 1060.67% similarVerifiedQwen2.5-Coder-32B running with Q4 quantization on an RTX 4090 can achieve an inference speed of 40–60 tokens per second.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/847696API
curl https://kongchang.com/api/v1/knowledge/claims/847696MCP
get_claim(id=847696)