Unverified50% confidenceBenchmarkExact time
An older RTX 3090, thanks to its 24 GB VRAM accommodating more experts, is estimated to achieve 100 to 140 tokens/second running Strata, indicating that under this workload VRAM capacity outweighs raw floating-point compute.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedA UP host running MiniCPM 2B with an RTX 4080S (16GB VRAM) + 64GB RAM configuration achieved an inference speed of approximately 110 tokens/second in real-world testing75% similarUnverifiedWhen 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.75% similarUnverifiedRTX 4090相比RTX 3060在推理场景下的实际吞吐量提升约3-4倍75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978621API
curl https://kongchang.com/api/v1/knowledge/claims/978621MCP
get_claim(id=978621)