Unverified60% confidenceFactTime unknown
Qwen3-235B-A22B adopts a MoE architecture, activating only 22B out of 235B total parameters at a time.
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Unsloth：本地微调大模型速度提升5倍的开源神器
githubunslothai
Related Entities
Related Claims
UnverifiedQwen3.5-122B-A10B is a MoE architecture model with approximately 122B total parameters and approximately 10B activated parameters.72% similarUnverifiedQwen3.8-27B is a dense architecture model, released in FP8 precision under the Apache-2.0 license, with a native context of 262,144 tokens, extensible to 1M.71% similarUnverifiedThe developer uses the Qwen3.6-35B-A3B model: it has 35B weights in total, uses only 3B weights when processing each word, has a computational cost comparable to ordinary 4B and 8B models, and runs on their own gateway (vLLM).70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/33220API
curl https://kongchang.com/api/v1/knowledge/claims/33220MCP
get_claim(id=33220)