Expired50% confidenceBenchmarkExact time
The model can achieve approximately 206 tokens/second on a single RTX 5090 using the NVFP4 scheme.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/5/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/19/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedWhen VRAM is sufficient and the model is fully resident on the GPU, an RTX 4090 running a Q4-quantized 27B model can typically achieve 15–30 tokens/s; once CPU offloading is triggered, the speed may drop sharply to 1–2 tokens/s or even lower.80% similarUnverifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.71% similarVerifiedA model with 70 billion parameters (70B) can run on a single RTX 4090 (24GB VRAM) after quantization.70% similarUnverifiedWhen batching 8 requests together, a single RTX PRO 6000 can achieve an aggregate throughput of approximately 220 output tok/s, whereas the old configuration of two RTX 3090s achieved only approximately 19 tok/s.70% similarUnverifiedThe RTX 4060 can achieve generation speeds 3-5 times that of the GTX 1060.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/862144API
curl https://kongchang.com/api/v1/knowledge/claims/862144MCP
get_claim(id=862144)