Unverified50% confidenceFactExact time
v0.30.0 adds support for models including GLM-5.3-Flash, K2-Horizon, Cohere Compass, and Bailing V3 VL.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedvLLM v0.29.0 added support for models including Hy4-preview, Qwen3.8-Flash-Next, GraniteSWA, and NemotronH Omni Reasoning V3.69% similarUnverifiedThe new version of Unsloth officially supports two models: Qwen3.8-Flash-Next and GLM-5.3-Flash.66% similarUnverifiedThree new models — VDN-H3, TaoMate H3, and LightX2V 1.2 — have been added to the H3 Acceleration Arena evaluation queue.64% similarUnverifiedThe Qwen3.8-27B model is available in multiple formats including Safetensors, GGUF, NVFP4, NVFP4 GGUF variants, and GPTQ-Int4 quantized versions.63% similarUnverifiedGLM-5 and GLM-5.1 have completed inference adaptation for 7 domestic chips: Huawei Ascend, Moore Threads, Cambricon, Kunlunxin, Metax, Enflame, and Hygon.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945479API
curl https://kongchang.com/api/v1/knowledge/claims/945479MCP
get_claim(id=945479)