Unverified50% confidenceBenchmarkExact time

Official benchmark results show that the Qwen3.6 35B MoE model can reach 1.38k token/s at 8 concurrency.

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

9/16/2026

First Seen

Valid until: 12/15/2026

Sources

Anifer Open-Source Inference Engine Benchmarked: Single RTX 5090 Hits 150 token/s

Related Entities

Qwen3.6 35Bmodel Aniferproduct

Related Claims

UnverifiedThe MoE version of Qwen3-235B has only approximately 22B parameters actually activated.75% similar VerifiedQwen3.6 27B scored 77.2 on SWE-bench Verified.72% similar UnverifiedThe vendor claims that the Ornith 35B MoE model is capable of surpassing Qwen 3.6 35B70% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/924350

API

curl https://kongchang.com/api/v1/knowledge/claims/924350

MCP

get_claim(id=924350)