Unverified50% confidenceFactExact time
This version supports exporting Clef models based on the Qwen3.5 backbone, as well as Laya models, to GGUF format.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedAll of these Qwen3 uncensored models provide GGUF format support and retain native MTP (Multi-Token Prediction) capability.74% similarUnverifiedThe Qwen3.8-27B model is available in multiple formats including Safetensors, GGUF, NVFP4, NVFP4 GGUF variants, and GPTQ-Int4 quantized versions.73% similarVerifiedOllama natively supports the GGUF format, and most models have been pre-quantized to specifications such as Q4_K_M or Q8_0.70% similarUnverifiedThe new version of Unsloth officially supports two models: Qwen3.8-Flash-Next and GLM-5.3-Flash.69% similarUnverifiedThe application has a built-in qwen3 4b model to enable out-of-the-box functionality68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984880API
curl https://kongchang.com/api/v1/knowledge/claims/984880MCP
get_claim(id=984880)