A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
47,133 repositories indexed
1–19 of 19 · Most stars
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
- fine-tuning
- llama
- llms
- gemma
The open-source AI voice studio. Clone, dictate, create.
- ai
- voice-clone
- qwen3-tts
- voice-ai
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- decision-model
- jev
- qwen3
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
- academia
- arxiv
- brave
- deep-research
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
- interpretability
- mechanistic-interpretability
- qwen
- steering
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
Implementing LLM architectures from scratch in PyTorch
- gemma3
- llama4
- llm
- moe
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
为 AI Agent 设计的哔哩哔哩命令行工具：扫码登录、看视频、评论、私信、发动态、投稿，全部 JSON 输出
- agent-skills
- ai-agent
- automation
- bilibili
An NES CPU compiled into the weights of a stock Qwen3.5 model