State of open code models (Sep 2025)
The best open code models on Hugging Face as of Sep 2025
Text Generation • 1T • Updated • 82.9k • • 2.33kNote Agent (https://docs.continue.dev/features/agent/)
Qwen/Qwen3-Coder-480B-A35B-Instruct
Text Generation • 480B • Updated • 82.4k • • 1.31kNote Agent (https://docs.continue.dev/features/agent)
zai-org/GLM-4.5
Text Generation • 358B • Updated • 52k • • 1.4kNote Agent (https://docs.continue.dev/features/agent/)
openai/gpt-oss-120b
Text Generation • 120B • Updated • 4.73M • • 4.59kNote Agent (https://docs.continue.dev/features/agent/)
zai-org/GLM-4.5-Air
Text Generation • 110B • Updated • 359k • • 588Note Agent (https://docs.continue.dev/features/agent/)
open-r1/OlympicCoder-32B
Text Generation • 33B • Updated • 24 • • 156Note Overall competitive coding (https://huggingface.co/blog/open-r1/update-3)
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 1.04M • • 978Note Agent (https://docs.continue.dev/features/agent/)
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.2M • • 1.92kNote Chat (https://docs.continue.dev/features/chat)
mistralai/Devstral-Small-2507
Updated • 37.5k • 363Note Agent (https://docs.continue.dev/features/agent/)
openai/gpt-oss-20b
Text Generation • 22B • Updated • 7.47M • • 4.46kNote Agent (https://docs.continue.dev/features/agent/)
continuedev/instinct
Text Generation • 8B • Updated • 221 • 69Note Next Edit (https://docs.continue.dev/features/autocomplete/next-edit)
Qwen/Qwen2.5-Coder-7B
Text Generation • 8B • Updated • 194k • • 139Note Autocomplete (https://docs.continue.dev/features/autocomplete)
open-r1/OlympicCoder-7B
Text Generation • 8B • Updated • 320 • • 183Note Local competitive coding (https://huggingface.co/blog/open-r1/update-3)
Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 548k • • 85Note Autocomplete (https://docs.continue.dev/features/autocomplete)