qwen3-5 开源项目推荐（100 个）

2U1 /Qwen-VL-Series-Finetune

阿里云对Qwen-BL系列进行微调的开源实现。

johnbean393 /KeyType

一位开源的共打者，支持macOS全系统AI自动补全

umbertogriffo /rag-chatbot

RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

sophgo /LLM-TPU

Run generative AI models in sophgo BM1684X/BM1688

albond /DGX_Spark_Qwen3.5-122B-A10B-AR-INT4

DGX Spark上的Qwen3.5-122B-A10B：28.3→51 tok/s（+80%）

jegly /OfflineLLM

Private on-device AI chat for Android - runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection. + GPU Acceleration - PQC ML-DSA-87 signed releases

aptdnfapt /qwen-code-oai-proxy

QWEN 代理。QWEN 代码 OauS 文件用于代理服务器，所以你可以使用 Qwen Coder Model，任何使用 OpenAI API 和基础 URL 的工具。 以及WebSearch API代理

akdeb /OpenToys

Make Local AI Toys, Robots, Devices that work with a MacBook and an Arduino ESP32

modelscope /mcore-bridge

MCore-Bridge：为前沿大模型提供 Megatron-Core 模型定义，让 Megatron 训练像 Transformers 一样简单——支持 300+ 大语言模型（Qwen3-Next、GLM-5.3、Deepseek-V4、MiniMax-2.7 等）和 200+ 多模态大模型（Qwen3.8、Qwen3-Omni、Gemma4 等）。

vixhal-baraiya /qwenFS

Qwen3.5-2B with a filesystem compiled and inserted directly into its weights.

ThetaCursed /ComfyUI-MOSSImageTextEncoder

ComfyUI node that feeds a reference image through the Qwen3.5-9B vision tower and injects its embeddings into the text prompt (MOSS-Image conditioning)

phuongncn /asus-gx10-qwen35-speed-hack

4-5x faster Qwen3.5 on ASUS GX10 / DGX Spark — Hybrid INT4+FP8 + MTP via one shell script

AkiYangDev /mini-deepinfer

Learn DeepInfer through a small, runnable inference engine. Follow the code on CPU, then run real Qwen3.5 models on Ascend 910C.

eduardoabreu81 /moss-image-forge-neo

MOSS-Image for Stable Diffusion WebUI Forge Neo: text-to-image with sharp English and Chinese text, img2img and layouts by boxes, with the SFT and Base models

mukel /qwen35.java

Fast Qwen 3.5 inference in pure Java

frankluise5220 /ComfyUI-Lorahelper

A professional automation toolkit for ComfyUI to prepare LoRA training data using LLMs. New support for Qwen 3.5

sandseb123 /local-lora-cookbook

Fine-tune a local LLM on your own app's data in 15 minutes. Runs entirely on-device, zero cloud after training. Apple Silicon + CUDA.

albond /DGX_Spark_Unsloth_Lossless_Speedup

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.

DeepakSingh98 /qwenlab

Six small transformers compiled into Qwen3.5-9B, trained in its own forward passes. Qwen runs the experiments.

Slocean /PulseCoreLite

PulseCoreLite is a desktop performance monitoring application based on Tauri 2 and Vue 3. It offers two forms of monitoring: floating window monitoring and taskbar monitoring. It displays real-time indicators such as CPU, GPU, memory, disk, and network, and supports system-level capabilities such as multiple languages, transparency and refresh rate