Unverified90% confidenceFactTime unknown
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
1
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQwen2.5、Gemma3 等系列均已推出专为边缘场景优化的 1B-3B 量化版本70% similarUnverifiedUnsloth added support for three new models: DiffusionGemma, Gemma 4 MTP, and MiniMax-M3.66% similarUnverifiedThe Qwen3.6 35B model natively supports MTP, and when combined with oMLX, the acceleration capability can be activated directly without any additional configuration of a separate draft model.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/35687API
curl https://kongchang.com/api/v1/knowledge/claims/35687MCP
get_claim(id=35687)