Unverified50% confidenceBenchmarkExact time
Strata is an open-source inference runtime capable of running the 125-billion-parameter Qwen3.8 Flash Next model on an RTX 5070 (12 GB VRAM) at an output speed of approximately 90 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
VerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.75% similarUnverifiedAn 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.72% similarUnverifiedQwen3.5 with approximately 800 million parameters achieved the fastest generation speed, approaching 15 tokens per second, with the second-place LFM2.5 exceeding 10 tokens per second.71% similarVerifiedOn the RTX 5090, Muse Glimmer's generation speed increases from 75 tokens per second to 233 tokens per second, a speedup of approximately 3.1×.69% similarUnverifiedDeveloper Primitive reported a generation speed of 142.6 tokens/s for Qwen3 Flash Next running locally.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978610API
curl https://kongchang.com/api/v1/knowledge/claims/978610MCP
get_claim(id=978610)