Tag: Qwen 3.8 Flash Next

Releases

vLLM v0.30.0 Release — Expanded Model Support and Model Runner V2 Enhancements

News

Tim Dettmers Announces Open Source Week to Showcase Local AI and Autonomous Research Ecosystems

Releases

mlx-vlm v0.7.0 Released — Expanded Model Support and inference Performance Optimizations

Releases

llama.cpp v0.4.0 Released — New Model Support and Memory Usage Optimizations

News

NVIDIA Releases FP4quantization Version of Qwen3.8-Flash-Next on Hugging Face

News

slotstream Released: Running 125B Qwen3.8-Flash-Next on 16GB Mac at Approx. 12 tok/s

Model Reports

DeepSeek-V4-Flash-Vision-Exp Evaluation Report

Releases

mlx-vlm v0.7.0rc0 Released — MTP Support for Qwen3.8-Flash-Next and Numerous Bug Fixes

Releases

llama-cpp b10712 Released: Vulkan Top-K Acceleration and Improved n-gram Generation Speed

Releases

koboldcpp v1.120 Released: DirectIO Support, New Models, and Bug Fixes

Releases

ollama v0.33.2 Released — Dark Mode Restored and MLX Features Added

Releases

mlx-vlm v0.6.16–17 Released: New Model Support and Metal Resource Leak Fixes

News

Qwen3.8-Flash-Next Weights Released as Early Preview of Qwen4 Architecture