Unverified50% confidenceBenchmarkExact time
According to the README, the 12 GB RTX 5070 achieves approximately 94 tokens/second, while the 32 GB RTX 5090 can exceed 250 tokens/second
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedOn an RTX 5070 with a 6-core Ryzen and 64 GB of memory, Strata achieves approximately 90 tokens/second for short conversations, approximately 67 tokens/second at a 128,000-token context, and approximately 1,300 tokens/second for reading prompts.80% similarUnverifiedA 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% similarVerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.75% similarUnverifiedIn an RTX 5060 Ti 16GB + 64GB RAM environment, Qwen3 27B took 1 hour and 10 minutes to generate a responsive personal website, averaging 6.42 tokens per second.74% similarUnverifiedThe desktop features an RTX 5070 graphics card and 32GB of 6000MHz memory73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003439API
curl https://kongchang.com/api/v1/knowledge/claims/1003439MCP
get_claim(id=1003439)