Unverified50% confidenceFactExact time
GLB-3D-Coder is trained based on Qwen3.5-4B.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQwen4, built on a next-generation architecture, has already entered training.73% similarUnverifiedThe project uses Tinker to perform supervised fine-tuning of Qwen3-8B.72% similarUnverifiedAt the core of NV-Reason-CT is a native 3D visual encoder whose output is fed into the QWEN 3.5 language model, with the two components trained jointly end-to-end.70% similarUnverifiedContinue's current configuration guide recommends using Qwen2.5-Coder 1.5B for the autocomplete role.67% similarUnverifiedThe Q4_0 file in the GGUF repository is a quantization-aware distillation (QAD) checkpoint, reportedly trained to recover the accuracy lost to Q4_0 quantization, but Liquid has not yet published actual accuracy figures.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125507API
curl https://kongchang.com/api/v1/knowledge/claims/1125507MCP
get_claim(id=1125507)