qwen3 repositories
Trending repositories tagged qwen3, ranked by trending score. Updated daily.
-
1
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub · Python · 97,255 stars · 25,073 forks · +109 stars in 24 hours · Trending score 4.26
-
2
synchopate/llama-modchip
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).
GitHub · Python · 1,387 stars · 134 forks · +38 stars in 24 hours · Trending score 3.55
-
3
JakeATX/llamAmpere
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
GitHub · C++ · 403 stars · 50 forks · +87 stars in 24 hours · Trending score 3.35
-
4
jaredpalmer/kev
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
GitHub · Python · 10,069 stars · 690 forks · +26 stars in 24 hours · Trending score 2.86
-
5
peonist-ai/halogen-flash-server
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.
GitHub · Shell · 1,403 stars · 101 forks · +17 stars in 24 hours · Trending score 2.66
-
6
sangharshadhyeta/Strata-HotRod
Run Qwen3.8-Flash-Next (125B) on an RTX 3060 12 GB with 30 GB of RAM, streaming experts from the SSD. 50-70 tok/s, 262K context. A fork of Strata.
GitHub · C++ · 37 stars · 3 forks · +24 stars in 24 hours · Trending score 2.53
-
7
modelscope/ms-swift
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).
GitHub · Python · 16,135 stars · 1,817 forks · +12 stars in 24 hours · Trending score 2.42
-
8
prabanta-dev/janas
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.
GitHub · C · 735 stars · 73 forks · +11 stars in 24 hours · Trending score 2.41
-
9
1Panel-dev/MaxKB
🔥 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。
GitHub · Python · 23,176 stars · 3,229 forks · +9 stars in 24 hours · Trending score 2.14
-
10
qualcomm/GenieX
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
GitHub · Go · 8,541 stars · 1,091 forks · +7 stars in 24 hours · Trending score 2.06
-
11
NVIDIA-NeMo/Automodel
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
GitHub · Python · 1,093 stars · 389 forks · +5 stars in 24 hours · Trending score 1.71
-
12
dolev31/ProactiveInquirer
Asking for What Was Never Requested: horizontal and vertical proactivity in LLM agents. Need-graph metrics (no LLM judge) and Q&D, which trains a questioner from the consequences of its questions.
GitHub · Python · 22 stars · 0 forks · +10 stars in 24 hours · Trending score 1.63
-
13
ShuaixinHuang/image-multiple-angles-3d-camera
🎬 Generate images from any camera viewpoint via 3D interactive control. Drag the camera in 3D space or use sliders to set azimuth/elevation/distance, then generate. Built with Three.js + Gradio, bilingual ZH/EN UI.
GitHub · Python · 1,005 stars · 21 forks · 0 stars in 24 hours · Trending score 1.51
-
14
lawrence3699/jev-style
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.
GitHub · Python · 137 stars · 4 forks · +1 stars in 24 hours · Trending score 1.47
-
15
jaedync/crucible-strix-halo
Run Qwen3.8-Flash-Next on one AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). EXL3 4.05 and 3.05 bpw packs, own ROCm/HIP kernels, OpenAI-compatible server, 4 sessions of 262K context, setup guide included.
GitHub · Python · 35 stars · 7 forks · +2 stars in 24 hours · Trending score 1.45
-
16
stdlogits/neuron-lens
A catalog of every MLP neuron and attention head of Qwen3-8B and Gemma 4 12B, read from the weights through two Jacobian lenses (R and S), from activations, and from their exact token drivers
GitHub · Python · 57 stars · 5 forks · +4 stars in 24 hours · Trending score 1.39
-
17
dwim-sh/dwim
dwim is a coding agent that you control. Local by default.
GitHub · Rust · 44 stars · 2 forks · +5 stars in 24 hours · Trending score 1.35
-
18
ARahim3/kaggle-tpu-lab
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.
GitHub · Python · 813 stars · 110 forks · +2 stars in 24 hours · Trending score 1.32
-
19
stdlogits/neuron-reflection
Swap, fuse, remove or split a concept in Qwen3-8B's weights, without training, by mirroring the neurons and attention heads that carry it
GitHub · Python · 16 stars · 2 forks · +11 stars in 24 hours · Trending score 1.30
-
20
shyringo/qwen3.8-27b-in-c
Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools; no GPU or Python. | 单颗笔记本 CPU 运行 Qwen3.8-27B:最快 2.52 token/s,最低 8 GB 内存可运行,推理加速不牺牲准确性。原生 OpenAI 兼容接口支持函数工具;无需 GPU 或 Python。
GitHub · C · 24 stars · 6 forks · +4 stars in 24 hours · Trending score 1.16
-
21
EvolvingLMMs-Lab/LLaVA-OneVision-2.5
Fully Open Framework for Democratized Multimodal Training
GitHub · Python · 1,236 stars · 78 forks · +4 stars in 24 hours · Trending score 1.14
-
22
zolotukhin/zinc
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
GitHub · Zig · 532 stars · 39 forks · +1 stars in 24 hours · Trending score 1.05
-
23
InfinityZero3000/LexiLingo
Next-gen AI language tutor utilizing a novel Trace-CAG pipeline for zero-hallucination pedagogical feedback
GitHub · Python · 50 stars · 8 forks · 0 stars in 24 hours · Trending score 1.02
-
24
meizhong986/WhisperJAV
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV
GitHub · Python · 2,467 stars · 208 forks · 0 stars in 24 hours · Trending score 0.95