Written by Jakub Rusinowski · Last updated July 10, 2026
Alibaba's dedicated coding line. The 480B-A35B flagship holds state-of-the-art among open models on SWE-bench Verified and agentic coding at release (Qwen positions it comparable to Claude Sonnet 4), while the 80B-A3B variant delivers most of that quality with only 3B active parameters — cheap enough to self-host. Best-in-class open weights for repo-level coding, debugging, and code review.
| Qwen3-Coder 8B | Min 6 GB VRAM · Q4_K_M · 128,000 ctx · ollama run qwen3-coder:8b |
| Qwen3-Coder 80B-A3B (MoE) | Min 49 GB VRAM · Q4_K_M · 128,000 ctx · ollama run qwen3-coder:80b-a3b-q4 |
| Qwen3-Coder 480B-A35B (MoE) | Min 291 GB VRAM · Q4_K_M · 256,000 ctx · ollama run qwen3-coder:480b-a35b |
The cheapest GPU that runs Qwen3-Coder locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run qwen3-coder:8b
Minimum VRAM: 6 GB. For best results use Q4_K_M quantization.
Qwen3-Coder needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Qwen3-Coder 8B (6 GB, Q4_K_M); Qwen3-Coder 80B-A3B (MoE) (49 GB, Q4_K_M); Qwen3-Coder 480B-A35B (MoE) (291 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Qwen3-Coder runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Qwen3-Coder in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run qwen3-coder:8b. This downloads Qwen3-Coder and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.