Repository Index

A high-throughput and memory-efficient inference and serving engine for LLMs

• gpt
• llm
• pytorch
• model-serving

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

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Translated🔥 MaxKB is an open-source platform for building enterprise-grade agents. A powerful and easy-to-use open-source enterprise-grade agent platform.

• llm
• ollama
• maxkb
• knowledgebase

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).

• llm
• lora
• sft
• multimodal

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!

• llms
• lora
• reinforcement-learning
• agent

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

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

• llm
• on-device-ai
• sdk
• vlm

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

• agent
• llm
• rag
• vector-database

Translated非线智能 NoneLinear (Non-linear Intelligence) - ReLE evaluation: capability evaluation of Chinese AI large models (continuously updated): it currently covers 374 large models, including commercial models such as chatgpt, gpt-5.4, Google gemini-3.1-pro, Claude-4.6, 文心 ERNIE-X1.1, ERNIE-5.0, qwen3.6-max, qwen3.6-plus, Baichuan, iFlytek Spark, and SenseTime senseChat, as well as open-source large models such as step3.5-flash, kimi-k2.6, ernie4.5, MiniMax-M2.7, deepseek-v4, Qwen3.6, llama4, Zhipu GLM-5.1, MiMo-V2, LongCat, gemma4, and mistral. It provides not only leaderboards but also a large model defect library with more than 2,000,000 entries! This makes it convenient for the broad community to research, analyze, and improve large models.

• agentic-ai
• artificial-intelligence
• llm-agent
• llm-evaluation

A Next-Generation Training Engine Built for Ultra-Large MoE Models

• llm
• agent
• deepseek-v3
• gpt-oss

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

• chromadb
• dashcam
• gemini
• gemini-embedding-2

Qwen3.8 is the large language model series developed by Qwen team, Alibaba Group.

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

• ai
• llama
• llm
• macos

Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results

• interpretability
• mechanistic-interpretability
• qwen
• steering

Fullstack SaaS Boilerplate built with tRPC, Fastify and React

• react
• tailwind
• trpc
• fastify

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

• amd
• gfx1151
• gpu-inference
• hip

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

Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).

• avx512
• cpu-inference
• hpc
• llama-cpp

Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.

• anthropic-api
• cuda
• gemma
• gguf

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

• avx2
• c
• cpu-inference
• gguf