Apps · Agent (needs a local model server)

Qwen Code

by Qwen · Apache-2.0 · 27,300 GitHub stars

Terminal coding agent from the Qwen team. Switch between cloud providers and local Ollama or vLLM models at runtime.

macOSWindowsLinux

Get Qwen Code

At a glance

Best for
Qwen coding models on your own machine.
Inference engine
  • uses llama.cpp, Ollama or LM Studio
GPU support
None of its own: it talks to a llama.cpp or MLX LM server
Opens
  • GGUF
  • MLX
Features
  • Agent workflows
  • Tool calling
Platforms
Terminal agent with IDE plugins. Supports local models through Ollama or vLLM.

Sources: github.com

Install

macOS

npm install -g @qwen-code/qwen-code@latest

Linux

npm install -g @qwen-code/qwen-code@latest

Windows

npm install -g @qwen-code/qwen-code@latest

Then start a model server for it: llama-server -hf <GGUF repo> on any OS, or mlx_lm.server --model <MLX repo> on a Mac, and point Qwen Code at http://127.0.0.1:8080/v1.

190 models on this site run in Qwen Code

Models built for tool use and coding, with a GGUF or MLX build to serve locally.

Model Made by Type Size Opens it as Quality tier
MiMo V2.6 Pro (1T-A42B) Xiaomi LLM 1,024B (42.0B active) GGUF or MLX 99
MiMo V2.6 Flash (310B-A15B) Xiaomi LLM 311B (15.0B active) GGUF or MLX 97.2
DeepSeek V4 Pro (1.6T-A49B) DeepSeek LLM 1,651B (49.0B active) GGUF 96.8
GLM-5.2 (753B-A40B) Zhipu AI LLM 753B (40.0B active) GGUF or MLX 96.3
Hunyuan Hy4 Preview (780B) Tencent LLM 780B (55.0B active) GGUF or MLX 96.3
Qwen3.8 Flash Next (125B-A6B) Alibaba LLM 180B (6.0B active) GGUF or MLX 96.5
DeepSeek V4 Pro (April 2026) DeepSeek LLM 1,599B (49.0B active) MLX 95
GLM-5.1 (744B-A40B) Zhipu AI LLM 754B (40.0B active) GGUF or MLX 95.2
GLM-5.3 Flash (320B-A18B) Zhipu AI LLM 321B (18.0B active) GGUF or MLX 95.4
Kimi K2.6 (1T) Moonshot AI LLM 1,027B (32.0B active) GGUF 95.7
Qwen3.5 397B-A17B Alibaba LLM 403B (17.0B active) GGUF or MLX 95
DeepSeek V4 Flash (284B-A13B) DeepSeek LLM 304B (13.0B active) GGUF 94
GLM-5 (744B-A40B) Zhipu AI LLM 754B (40.0B active) GGUF or MLX 94.7
Hunyuan Hy3 (295B-A21B) Tencent LLM 299B (21.0B active) GGUF 94.4
Kimi K2.5 (1T) Moonshot AI LLM 1,027B (32.0B active) GGUF or MLX 94.3
Kimi K2.7 Code (1T) Moonshot AI LLM 1,027B (32.0B active) GGUF or MLX 94.3
MiniMax M3 (427B) MiniMax LLM 427B (25.0B active) GGUF or MLX 94.8
Ornith 1.5 397B-A17B DeepReinforce LLM 403B (17.0B active) GGUF 94
Qwen3.6 27B Alibaba LLM 28B GGUF or MLX 94
DeepSeek R1 0528 (671B) DeepSeek LLM 685B (37.0B active) GGUF or MLX 93
DeepSeek V3.2 (671B) DeepSeek LLM 685B (37.0B active) GGUF or MLX 93.7
GLM-4.7 (355B-A32B) Zhipu AI LLM 358B (32.0B active) GGUF or MLX 93.5
Kimi K2 Thinking (1T) Moonshot AI LLM 1,026B (32.0B active) GGUF or MLX 93
MiniMax M2.7 (230B-A10B) MiniMax LLM 229B (10.0B active) GGUF or MLX 93.5
Nemotron 3 Ultra 550B-A55B NVIDIA LLM 561B (55.0B active) GGUF 93.2
DeepSeek V4 Flash (April 2026) DeepSeek LLM 291B (13.0B active) GGUF or MLX 92
Gemma 4 26B-A4B Google LLM 26B (3.8B active) GGUF or MLX 92.5
MiniMax M2.5 (230B-A10B) MiniMax LLM 229B (10.0B active) GGUF or MLX 92.5
Qwen3.5 122B-A10B Alibaba LLM 125B (10.0B active) GGUF or MLX 92
Step 3.5 Flash (196B-A11B) StepFun LLM 199B (11.0B active) GGUF or MLX 92
DeepSeek V3.1 (671B) DeepSeek LLM 685B (37.0B active) GGUF or MLX 91
DeepSeek V3.1 Terminus DeepSeek LLM 685B (37.0B active) GGUF or MLX 91.5
Gemma 4 31B Google LLM 31B GGUF or MLX 91
Kimi K2 Instruct 0905 (1T) Moonshot AI LLM 1,026B (32.0B active) GGUF or MLX 91
MiniMax M2.1 (230B-A10B) MiniMax LLM 229B (10.0B active) GGUF or MLX 91
Qwen3 235B-A22B Thinking 2507 Alibaba LLM 235B (22.0B active) GGUF or MLX 91
Qwen3 Coder 480B-A35B Alibaba LLM 480B (35.0B active) GGUF or MLX 91
Ling 1T Ant Group (inclusionAI) LLM 1,000B (50.0B active) GGUF 90
MiMo V2 Flash (309B-A15B) Xiaomi LLM 310B (15.0B active) GGUF or MLX 90.9
Mistral Large 3 (675B) Mistral AI LLM 675B (41.0B active) GGUF 90
Qwen3 235B-A22B Instruct 2507 Alibaba LLM 235B (22.0B active) GGUF or MLX 90
Apodex 1.1 Mini (35B-A3B) Apodex LLM 36B (3.0B active) GGUF 89
Kimi K2 Instruct (July 2025) Moonshot AI LLM 1,026B (32.0B active) GGUF or MLX 89
MiniMax M2 (230B-A10B) MiniMax LLM 229B (10.0B active) GGUF or MLX 89
Qwen3-VL 235B-A22B Instruct Alibaba LLM 236B (22.0B active) GGUF or MLX 89
Fara 1.5 27B Microsoft LLM 27B GGUF 88
GLM-4.7 Flash (30B-A3B) Zhipu AI LLM 31B (3.0B active) GGUF or MLX 88
K-EXAONE 236B-A23B LG AI Research LLM 237B (23.0B active) GGUF or MLX 88
LongCat Flash Chat (560B) Meituan LLM 562B (27.0B active) GGUF or MLX 88
Nemotron 3 Super 120B-A12B NVIDIA LLM 124B (12.0B active) GGUF 88
Agents-A1 35B-A3B InternScience LLM 35B (3.0B active) GGUF or MLX 87
Qwen AgentWorld 35B-A3B Alibaba LLM 35B (3.0B active) GGUF or MLX 87
Devstral 2 (123B) Mistral AI LLM 125B GGUF or MLX 86
Laguna S 2.1 (118B-A8B) Poolside LLM 118B (8.0B active) GGUF or MLX 86
Llama 3.1 Nemotron Ultra 253B v1 NVIDIA LLM 253B GGUF 86
Qwen3 Coder Next (80B-A3B) Alibaba LLM 80B (3.0B active) GGUF or MLX 86
Qwen3-Next 80B-A3B Thinking Alibaba LLM 81B (3.0B active) GGUF or MLX 86
UI-Mate 27B Tencent LLM 27B GGUF 86
GLM-4.6 (355B-A32B) Zhipu AI LLM 357B (32.0B active) GGUF or MLX 84
Qwen3 Next 80B-A3B Instruct Alibaba LLM 81B (3.0B active) GGUF or MLX 84
DeepSeek V3 0324 (671B) DeepSeek LLM 685B (37.0B active) GGUF or MLX 83
Gemma 4 12B Google LLM 12B GGUF or MLX 83
GLM-4.6V Zhipu AI LLM 108B (12.0B active) GGUF or MLX 83
Command A Reasoning (111B) Cohere LLM 111B GGUF or MLX 82
EXAONE 4.5 33B LG AI Research LLM 34B GGUF 82
GLM-4.5 (355B-A32B) Zhipu AI LLM 358B (32.0B active) GGUF or MLX 82
Ling 3.0 Flash (127B-A5B) Ant Group (inclusionAI) LLM 127B (5.1B active) GGUF 82
Command A (111B) Cohere LLM 111B GGUF or MLX 80
GLM-4.5V Zhipu AI LLM 108B (12.0B active) GGUF or MLX 80
Hermes 4 405B Nous Research LLM 406B GGUF or MLX 80
Kimi Dev 72B Moonshot AI LLM 73B GGUF or MLX 80
Llama 3.3 Nemotron Super 49B v1.5 NVIDIA LLM 50B GGUF or MLX 80
Mistral Large 2.1 (2411) Mistral AI LLM 123B GGUF 80
Mistral Medium 3.5 (128B) Mistral AI LLM 128B GGUF or MLX 80.4
Mistral Small 4 (119B-A6B) Mistral AI LLM 119B (6.0B active) GGUF or MLX 80.6
North Mini Code 1.0 (30B-A3B) Cohere LLM 30B (3.0B active) GGUF or MLX 80
Seed-OSS 36B Instruct ByteDance LLM 36B GGUF or MLX 80
Solar Open 100B Upstage LLM 103B (12.0B active) GGUF or MLX 80
Trinity Large Thinking (400B-A13B) Arcee AI LLM 399B (13.0B active) GGUF or MLX 80.3
Hermes 4.3 36B Nous Research LLM 36B GGUF 79
DiffusionGemma 26B-A4B IT Google LLM 26B (4.0B active) GGUF or MLX 78
GLM-4.5 Air (106B-A12B) Zhipu AI LLM 110B (12.0B active) GGUF or MLX 78
Qwen3 30B-A3B Thinking 2507 Alibaba LLM 31B (3.3B active) GGUF or MLX 78
Qwen3 Coder 30B-A3B Alibaba LLM 31B (3.3B active) GGUF or MLX 78
Qwen3-VL 32B Instruct Alibaba LLM 33B GGUF or MLX 78
QwQ 32B Alibaba LLM 33B GGUF or MLX 78
Ring Flash 2.0 (100B-A6B) Ant Group (inclusionAI) LLM 103B (6.1B active) GGUF 78
Nemotron 3 Nano 30B-A3B NVIDIA LLM 32B (3.5B active) GGUF 77
Qwen3 30B-A3B Instruct 2507 Alibaba LLM 31B (3.3B active) GGUF or MLX 77
Granite 4.2 30B IBM LLM 29B GGUF or MLX 76
Ling Flash 2.0 (100B-A6B) Ant Group (inclusionAI) LLM 103B (6.1B active) GGUF 76
Olmo 3.1 32B Think Ai2 LLM 32B GGUF or MLX 76
OpenReasoning Nemotron 32B NVIDIA LLM 33B GGUF or MLX 76
Skywork OR1 32B Skywork LLM 33B GGUF 76
DeepSeek Coder V2 (236B) DeepSeek LLM 236B (21.0B active) GGUF 74
GLM-4 32B 0414 Zhipu AI LLM 33B GGUF or MLX 74
GLM-Z1 32B (0414) Zhipu AI LLM 33B GGUF or MLX 74
Hermes 4 70B Nous Research LLM 71B GGUF or MLX 74
Hunyuan A13B (80B-A13B) Tencent LLM 80B (13.0B active) GGUF or MLX 74
Qwen3 30B-A3B Alibaba LLM 31B (3.3B active) GGUF or MLX 74
Qwen3-VL 30B-A3B Instruct Alibaba LLM 31B (3.3B active) GGUF or MLX 74
Apriel 1.5 15B Thinker ServiceNow LLM 15B GGUF or MLX 72
DeepSeek Coder V2 Instruct (0614) DeepSeek LLM 236B (21.0B active) GGUF 72
DeepSeek R1 Distill Qwen 32B DeepSeek LLM 33B GGUF or MLX 72
DeepSeek V2.5 1210 DeepSeek LLM 236B (21.0B active) GGUF or MLX 72
Granite 4.1 30B IBM LLM 29B GGUF or MLX 72
Llama 4 Maverick (17B x 128E) Meta LLM 402B (17.0B active) GGUF or MLX 72
Nemotron 3.5 Lightning 30B-A3B NVIDIA LLM 32B (3.0B active) GGUF 72
Command R+ (08-2024) 104B Cohere LLM 104B GGUF or MLX 70
DeepSeek V2.5 DeepSeek LLM 236B (21.0B active) GGUF 70
gpt-oss 20B OpenAI LLM 21B (3.6B active) GGUF or MLX 70
OpenHands LM 32B All Hands AI LLM 33B GGUF or MLX 70
UI-Mate 9B Tencent LLM 9.4B GGUF 70
UI-Venus 2 9B Ant Group (inclusionAI) LLM 9.4B GGUF 70
Granite 4.2 8B IBM LLM 8.8B GGUF or MLX 68
Hermes 3 (Llama 3.1 70B) Nous Research LLM 71B GGUF or MLX 68
Mistral Small 3.2 24B Mistral AI LLM 24B GGUF or MLX 68
Qwen2.5 Coder 32B Instruct Alibaba LLM 33B GGUF or MLX 67
AceReason Nemotron 14B NVIDIA LLM 15B GGUF or MLX 66
Apriel Nemotron 15B Thinker ServiceNow LLM 15B GGUF 66
Devstral Small 2505 Mistral AI LLM 24B GGUF or MLX 66
Hermes 4 14B Nous Research LLM 15B GGUF or MLX 66
Mistral Small 3.1 24B Mistral AI LLM 24B GGUF or MLX 66
OpenReasoning Nemotron 14B NVIDIA LLM 15B GGUF 66
Qwen2.5 Coder 14B Instruct Alibaba LLM 15B GGUF or MLX 66
Reka Flash 3.1 (21B) Reka AI LLM 21B GGUF or MLX 66
Trinity Mini (26B-A3B) Arcee AI LLM 26B (3.0B active) GGUF or MLX 66
Command R+ 104B (04-2024) Cohere LLM 104B GGUF or MLX 64
DeepCoder 14B Preview Agentica LLM 15B GGUF or MLX 64
Mistral Small 3 24B (2501) Mistral AI LLM 24B GGUF or MLX 64
Qwen2 72B Instruct Alibaba LLM 73B GGUF or MLX 64
Codestral 22B Mistral AI LLM 22B GGUF or MLX 62
Granite 4.0 H Small (32B-A9B) IBM LLM 32B (9.0B active) GGUF or MLX 62
JanusCoder 14B Shanghai AI Lab LLM 15B GGUF 62
Qwen3-VL 8B Instruct Alibaba LLM 8.8B GGUF or MLX 62
Agents-A1 4B InternScience LLM 4.5B GGUF 60
Granite 4.1 8B IBM LLM 8.8B GGUF or MLX 60
Fara 1.5 4B Microsoft LLM 4.5B GGUF or MLX 58
Seed-Coder 8B Reasoning ByteDance LLM 8.3B GGUF or MLX 58
LFM2 24B-A2B Liquid AI LLM 24B (2.3B active) GGUF or MLX 56
Seed-Coder 8B Instruct ByteDance LLM 8.3B GGUF or MLX 56
Qwen2.5 Coder 7B Instruct Alibaba LLM 7.6B GGUF or MLX 55
OpenReasoning Nemotron 7B NVIDIA LLM 7.6B GGUF 54
DeepSeek Coder V2 Lite (16B) DeepSeek LLM 16B (2.4B active) GGUF or MLX 52
Granite 4.2 3B IBM LLM 3.7B GGUF or MLX 52
LFM2.5 8B-A1B Liquid AI LLM 8.5B (1.5B active) GGUF or MLX 52
Fara 7B Microsoft LLM 8.3B GGUF or MLX 50
Hermes 3 (Llama 3.1 8B) Nous Research LLM 8.0B GGUF or MLX 48
CodeGeeX4 All 9B Zhipu AI LLM 9.4B GGUF 46
Dolphin 3.0 Llama 3.1 8B Cognitive Computations LLM 8.0B GGUF or MLX 46
Granite 4.1 3B IBM LLM 3.4B GGUF or MLX 46
Code Llama 70B Instruct Meta LLM 69B GGUF or MLX 44
DeepSeek Coder 33B Instruct DeepSeek LLM 33B GGUF 44
Dolphin 2.9.4 Llama 3.1 8B Cognitive Computations LLM 8.0B GGUF or MLX 44
Granite 3.1 8B Instruct IBM LLM 8.2B GGUF 44
Granite 4.0 H Tiny (7B-A1B) IBM LLM 6.9B (1.0B active) GGUF or MLX 44
Hermes 2 Pro Llama 3 8B Nous Research LLM 8.0B GGUF or MLX 44
OpenChat 3.6 8B OpenChat LLM 8.0B GGUF or MLX 44
Qwen2 7B Instruct Alibaba LLM 7.6B GGUF or MLX 44
Granite 4.0 Micro (3B) IBM LLM 3.4B GGUF or MLX 40
Granite Code 34B Instruct IBM LLM 34B GGUF 40
StarCoder2 15B Instruct BigCode LLM 16B GGUF or MLX 40
Yi Coder 9B Chat 01.AI LLM 8.8B GGUF or MLX 40
Code Llama 34B Instruct Meta LLM 34B GGUF or MLX 38
Dolphin 2.9 Llama 3 8B Cognitive Computations LLM 8.0B GGUF or MLX 38
Granite 4.0 H Micro IBM LLM 3.2B GGUF or MLX 38
Codestral Mamba 7B Mistral AI LLM 7.3B MLX 36
Granite Code 20B Instruct IBM LLM 20B GGUF 36
Hermes 2 Pro Mistral 7B Nous Research LLM 7.2B GGUF or MLX 36
Qwen2.5 Coder 3B Instruct Alibaba LLM 3.1B GGUF or MLX 36
OpenChat 3.5 (0106) OpenChat LLM 7.2B GGUF or MLX 35
CodeGemma 7B Google LLM 8.5B GGUF or MLX 34
DeepSeek Coder 6.7B Instruct DeepSeek LLM 6.7B GGUF 34
OpenChat 3.5 (1210) OpenChat LLM 7.2B GGUF 34
Granite Code 8B Instruct (128K) IBM LLM 8.1B GGUF 32
StarCoder2 15B (base) BigCode LLM 16B GGUF or MLX 32
Code Llama 13B Instruct Meta LLM 13B GGUF or MLX 30
SQLCoder 7B v2 Defog LLM 6.7B GGUF 30
Qwen2.5 Coder 1.5B Instruct Alibaba LLM 1.5B GGUF or MLX 26
StarCoder 15B BigCode LLM 16B GGUF 26
StarCoder2 3B BigCode LLM 3.0B GGUF or MLX 26
Code Llama 7B Instruct Meta LLM 6.7B GGUF or MLX 24
StarCoder2 7B BigCode LLM 7.2B GGUF or MLX 24
Granite Code 3B Instruct (128K) IBM LLM 3.5B GGUF 20
Stable Code Instruct 3B Stability AI LLM 2.8B GGUF or MLX 20
Phi-2 2.7B Microsoft LLM 2.8B GGUF or MLX 16
Yi Coder 1.5B Chat 01.AI LLM 1.5B GGUF 16
CodeGemma 2B Google LLM 2.5B GGUF or MLX 14
DeepSeek Coder 1.3B Instruct DeepSeek LLM 1.4B GGUF or MLX 12
Qwen2.5 Coder 0.5B Instruct Alibaba LLM 0.5B GGUF or MLX 8

Alternatives

Pi Hermes Agent OpenClaw OpenCode Codex CLI OpenHands Zed Cline Open Interpreter Goose Aider Tabby Crush Kilo Code Open WebUI AnythingLLM Khoj Letta

Which app should I use?

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.