Written by Jakub Rusinowski · Last updated 2026-07-12 · Hardware figures computed by our VRAM engine
Qwen3-Coder 8B runs on any 8 GB GPU (`ollama pull qwen3-coder:8b`). The 80B-A3B — the best coder most people can self-host — wants ~49 GB all-in-VRAM (2×24 GB or a 96 GB+ Mac) but runs on ~8 GB VRAM + 32 GB RAM via llama.cpp expert offload. The 480B-A35B flagship needs ~290 GB: admire it over an API. All three are Apache 2.0.
Qwen3-Coder is the family this hub recommends more than any other, for one reason: it's the strongest *dedicated* open coding line you can actually download — the 480B flagship set the open state of the art on SWE-bench Verified (69.6%), and the smaller sizes inherit its training. Apache 2.0 across the board, fill-in-the-middle support for autocomplete, and first-class Ollama tags.
The family spans a 36× size range, so "can I run it?" has three very different answers:
Q4_K_M figures from our compute engine. The 80B-A3B row shows the all-in-VRAM (fastest) case — see the offload section below.
| Model | VRAM (Q4) | Runs on | Context | License |
|---|---|---|---|---|
| Qwen3-Coder 8B The one everyone can run — Current-gen quality on an 8 GB card; FIM-tuned, so it doubles as the autocomplete model. ollama pull qwen3-coder:8b | 5.6 GB | 8 GB GPU (RTX 3060/4060) Mac: 16 GB unified | 125K | Apache-2.0 |
| Qwen3-Coder 80B-A3B (MoE) The self-hosting prize — ~96% of the flagship’s quality; 3B active params mean it generates faster than dense models half its size. ollama pull qwen3-coder:80b-a3b-q4 | 49.1 GB | 2×48 GB GPUs / big unified memory Mac: 96 GB unified | 125K | Apache-2.0 |
| Qwen3-Coder 480B-A35B (MoE) The API model — Open SoTA at release — and ~290 GB at Q4. Datacenter hardware or a hosted endpoint. ollama pull qwen3-coder:480b-a35b | 290.6 GB | Multi-GPU server — or use an API Mac: 512 GB unified | 256K | Apache-2.0 |
With Ollama installed:
ollama pull qwen3-coder:8b
ollama run qwen3-coder:8b "refactor this to use a context manager: ..."For the 80B on capable hardware:
ollama pull qwen3-coder:80b-a3b-q4Then wire it into VS Code with Continue or Cline — the end-to-end setup guide covers the config. For agent work, raise the context window (16K minimum) as described there; Qwen3-Coder supports long contexts, but your KV-cache VRAM is the real ceiling — model your exact card + context in the checker.
Because only ~3B parameters activate per token, llama.cpp (and recent Ollama builds) can keep the shared layers plus active experts in VRAM and page the rest from system RAM. In practice: ~8 GB VRAM + 32 GB system RAM runs the 80B-A3B at usable-but-not-snappy speeds — a couple of tokens per second slower than all-in-VRAM, dramatically better quality than anything else an 8 GB card can touch.
When it's worth it: delegated tasks where you fire an Aider/Cline job and review the result. When it isn't: interactive autocomplete — keep the 8B for that. This is the single best quality-per-dollar trick in local coding right now, and it's why we list system RAM as a real spec, not an afterthought.
The 8B is happy on almost anything; the 80B-A3B all-in-VRAM is the reason 24 GB cards get bought in pairs. If you’re specifying a machine around this model line:
Want to feel the 80B-A3B before committing to hardware? Rent a 48 GB+ instance for an hour and run it all-in-VRAM.
Full list on the cloud AI directory.