Unverified50% confidenceFactExact time
Miso supports embedding the local small models SmolLM2 or Qwen2.5, and can be replaced with any compatible .gguf model
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedThis version supports exporting Clef models based on the Qwen3.5 backbone, as well as Laya models, to GGUF format.69% similarUnverifiedXiaomi distilled a MiMo v2.6 Distilled Qwen 9B version oriented toward agentic programming, making it more accessible to general users.66% similarUnverifiedThe new version of Unsloth officially supports two models: Qwen3.8-Flash-Next and GLM-5.3-Flash.65% 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65% similarUnverifiedThe Qwen3.6 series does not support Fill-in-the-Middle (FIM), and it is recommended to retain Qwen2.5 Coder for real-time code completion.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999776API
curl https://kongchang.com/api/v1/knowledge/claims/999776MCP
get_claim(id=999776)