Unverified50% confidenceFactExact time
LFM2.5-24B-A2B and Qwen3.6-35B-A3B are both open-source, locally deployable MoE architecture models, with hardware requirements within the range of high-end consumer devices
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedThe Agent's default self-hosted configuration uses the Qwen3.6-35B-A3B model with 4-bit quantization deployed via sglang.72% similarUnverifiedThis deployment solution is based on an open-source project by an overseas developer and can run the Qwen3.8-Flash-Next model on an ordinary desktop computer, supporting 30/40/50-series NVIDIA GPUs and even AMD GPUs.71% similarUnverified可用于本地部署的模型从轻量级的Phi-3、Gemma到重量级的Llama 3、Qwen2.5都可以根据硬件条件自由切换71% similarUnverifiedQwen3.6-27B采用稠密（Dense）架构，而非MoE（Mixture of Experts）架构70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036174API
curl https://kongchang.com/api/v1/knowledge/claims/1036174MCP
get_claim(id=1036174)