The most recognized open LLMs for coding

The most popular and widely-recognized open LLMs built or tuned for code — Qwen-Coder, DeepSeek-Coder, Code Llama and the rest — each with the honest, $0-markup cost to run it on your own machine, a rented GPU, or your own API key. We list the recognized coding models with transparent run costs; which one writes the best code for your stack is yours to judge.

How this is ranked: We do NOT rank coding quality or quote benchmarks we didn't run. The 'coding' set is an objective tag/modality filter; within it we order by an objective signal (popularity/HF recognition) with honest run-costs, framed explicitly as 'the recognized open coding models — judge quality yourself.' That makes 'best' an objective filter, not our verdict.

• 1. Qwen2.5-Coder 32B Instruct — Alibaba, 32B · ~25 GB VRAM · $0.83/1M API · commercial OK
• 2. Qwen2.5-Coder 7B Instruct — Alibaba, 7B · ~7.0 GB VRAM · $0.16/1M API est. · commercial OK
• 3. Qwen2.5 Coder 14B Instruct — Qwen, 14.8B · ~14 GB VRAM · $0.22/1M API est. · commercial OK
• 4. Qwen3 Coder 30B A3B Instruct — Qwen, 30.5B · ~22 GB VRAM · $0.18/1M API · commercial OK
• 5. DeepSeek-Coder-V2-Lite Instruct — DeepSeek, 15.7B · ~11 GB VRAM · $0.23/1M API est. · commercial OK
• 6. Qwen3 Coder Next — Qwen, 79.7B · ~55 GB VRAM · $0.46/1M API · commercial OK
• 7. Qwen2.5 Coder 1.5B Instruct — Qwen, 1.5B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK
• 8. Qwen2.5 Coder 3B — Qwen, 3.1B · ~4.0 GB VRAM · $0.12/1M API est. · non-commercial
• 9. deepseek coder 7b instruct v1.5 — deepseek-ai, 6.9B · ~8.0 GB VRAM · $0.16/1M API est. · non-commercial
• 10. Qwen2.5 Coder 7B — Qwen, 7.6B · ~7.0 GB VRAM · $0.16/1M API est. · commercial OK
• 11. CodeLlama 7b hf — codellama, 6.7B · ~14 GB VRAM · $0.15/1M API est. · commercial OK
• 12. Qwen2.5 Coder 1.5B — Qwen, 1.5B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK
• 13. deepseek coder 6.7b instruct — deepseek-ai, 6.7B · ~14 GB VRAM · $0.15/1M API est. · non-commercial
• 14. xflux text encoders — XLabs-AI, 4.8B · ~8.0 GB VRAM · $0.14/1M API est. · commercial OK
• 15. Qwen2.5 Coder 3B Instruct — Qwen, 3.1B · ~4.0 GB VRAM · $0.12/1M API est. · non-commercial
• 16. starcoder2 3b — bigcode, 3B · ~4.0 GB VRAM · $0.12/1M API est. · commercial OK
• 17. Qwen2.5 Coder 0.5B Instruct — Qwen, 500M · ~2.0 GB VRAM · $0.10/1M API est. · commercial OK
• 18. CodeQwen1.5 7B Chat — Qwen, 7.3B · ~7.0 GB VRAM · $0.16/1M API est. · non-commercial
• 19. Qwen2.5 Coder 14B — Qwen, 14.8B · ~14 GB VRAM · $0.22/1M API est. · commercial OK
• 20. deepseek coder 1.3b instruct — deepseek-ai, 1.3B · ~6.0 GB VRAM · $0.11/1M API est. · non-commercial
• 21. gemma 4 12B coder fable5 composer2.5 v1 — yuxinlu1, 12B · ~14 GB VRAM · $0.20/1M API est. · commercial OK
• 22. IQuest Coder V1 40B Instruct — IQuestLab, 39.8B · ~33 GB VRAM · $0.42/1M API est. · non-commercial
• 23. starcoder — bigcode, 15.8B · ~19 GB VRAM · $0.23/1M API est. · commercial OK
• 24. Qwen3 Coder 480B A35B Instruct — Qwen, 480.2B · ~325 GB VRAM · $0.65/1M API · commercial OK
• 25. Qwopus3.6 27B Coder — Jackrong, 27.8B · ~33 GB VRAM · $0.32/1M API est. · commercial OK
• 26. starcoder2 7b — bigcode, 7.2B · ~7.0 GB VRAM · $0.16/1M API est. · commercial OK
• 27. Qwopus3.6 35B A3B Coder — Jackrong, 36B · ~42 GB VRAM · $0.39/1M API est. · commercial OK
• 28. KAT Coder V2.5 Dev — Kwaipilot, 34.7B · ~40 GB VRAM · $0.38/1M API est. · commercial OK
• 29. North Mini Code 1.0 — CohereLabs, 30.5B · ~22 GB VRAM · $0.34/1M API est. · commercial OK
• 30. Qwen3 Coder 30B A3B Instruct FP4 — NVFP4, 15.6B · ~12 GB VRAM · $0.22/1M API est. · commercial OK
• 31. OpenCoder 8B Instruct — infly, 7.8B · ~7.0 GB VRAM · $0.16/1M API est. · non-commercial

More: all "best" lists · Outcome Lab · all models

Open the free Spanvero advisor → · Honest, $0-markup. © 2026 Cynosure LLC.