A highly quantized (Q4_K_XL) version of the massive 397B parameter Qwen 3.5 model using an unusual layer-wise (UD) distribution format. It supports multimodal inputs and tool calling. Intended for advanced users running large models locally or in specialized inference environments.
Qwen3.5 397B A17B UD Q4 K XL Layers is a Foundation models & chat project. It focuses on enabling inference of very large Qwen 3.5 models on consumer or enterprise hardware through aggressive quantization and layer splitting. It is built as an open-source project for developers. Qwen3.5 397B A17B UD Q4 K XL Layers is open source under the Apache-2.0 license. It ships for the web, the command line, and API, and it can be self-hosted.
MeshLLM builds and maintains Qwen3.5 397B A17B UD Q4 K XL Layers, and it first shipped in 2026. The project is developed in the open on GitHub with 2.8k stars and 522 commits in the last 90 days. Key capabilities include Quantized Weights, Layer-wise Format, and Tool Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do