AI Briefing#qwen
The latest AI and developer news about #qwen, with the original source and a short summary.
The latest AI and developer news about #qwen, with the original source and a short summary.
Escha Labs released a 2-bit quantized model of Qwen3.8-27B, demonstrating performance equivalent to FP8.
AirLLM has been updated to enable Kimi K3 (2.8T) to run on 4GB VRAM via sparse MoE model streaming.
Agent Lightning v1.0 has been released as an RL training framework leveraging agent harnesses.
An abliterated version of Qwen3.8-27B with censorship removed has been released in MLX format for Apple Silicon.
Qwen3.6-35B is faster in speed but has longer inference times, resulting in slower final response times.
The open-source tool 'Profile' has been released to diagnose vLLM inference performance, identify bottlenecks, and optimize them.
Alibaba's Qwen3.8 27B model recorded 52 points on the Artificial Analysis Intelligence Index.
Released an MLX quantized version of Qwen3.8-27B with safety alignment removed for Apple Silicon.
Qwen has released a new ablation technique based on Qwen 27B that allows real-time adjustment of model refusal tendencies without reloading weights.
Alibaba's Qwen3.8 27B model achieved a score of 52 on the Artificial Analysis Intelligence Index.
Tencent has released an ultra-lightweight, high-performance multilingual Visual Document Retrieval (VDR) model based on Qwen3.5-4B.
WarpQuant, a 3.62 bpw quantization method combining Hadamard rotation and Output-Fisher recovery to enhance Qwen 27B performance, has been released.
The latest commit to the MS-Swift GitHub repository confirms support for the Qwen 3.8 35B MoE model.
China is securing AI competitiveness through its open model ecosystem and drastic reductions in inference costs.
A bug has been reported where llama.cpp's llama-server fails to pass the reasoning_effort parameter to the chat template.
Analyzed the vision tower structure and benchmark performance characteristics of the Qwen3.8-27B model.
Analyzed the KV cache capacity and memory requirements of the Qwen3.8-27B model based on context length.
The next-generation open model Qwen3.8-27B, with enhanced coding and vision capabilities, has been released.
Qwen has released the open model Qwen3.8 with a total of 2.4T parameters and 95B active parameters.
Qwen has released the Qwen3.8 open model with a total size of 2.4T and 95B active parameters.
Qwen has released a voice agent runtime that maintains conversations during background tasks.
LlamaIndex has released an open-source benchmark for evaluating schema-based information extraction.
QwenLM's Qwen-MM-Plugins repository is publicly available on GitHub.
Analyzed the independent development of LLMs using public configurations, tokenizers, and weights.