// Coding agents

Run Qwen3-Coder Locally: 8B, 80B-A3B, and the 480B Question

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Qwen3-Coder ships at 30B-A3B and above: the 30B-A3B (~18 GB at Q4) fits a 24 GB card (`ollama pull qwen3-coder:30b`). 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.

Written by Jakub Rusinowski · Last updated August 4, 2026 · Hardware figures computed by our VRAM engine

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:

The three sizes, honestly

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-Next (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	256K	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

Getting started in two commands

With Ollama installed:

ollama pull qwen3-coder:30b
ollama run qwen3-coder:30b "refactor this to use a context manager: ..."

For the 80B on capable hardware:

ollama pull qwen3-coder:80b-a3b-q4

Then 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.

The expert-offload trick: 80B-A3B on a gaming PC

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.

Which size should you run?

8 GB card / 16 GB Mac → 8B as your everything-model. Add StarCoder2 3B only if you want even faster ghost text.
16–24 GB card → the 30B-A3B, and honestly consider Qwen 3.6 27B or Devstral Small 2 24B for chat/agent work — at this tier the general Qwen 3.6 line edges the mid Coder sizes.
32 GB+ RAM regardless of GPU → try the 80B-A3B with offload for delegated tasks. It costs nothing but disk space to test.
2×24 GB / 96 GB+ Mac → 80B-A3B all-in-VRAM. This is the best local coding experience currently attainable without a server room.
Need the 480B → hosted endpoints (see the cloud directory) — same weights, same Apache 2.0, someone else's 290 GB.

Hardware that fits the family

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:

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

NVIDIA GeForce RTX 4090 24GB

24 GB VRAM · 450 W board power

2026 prices are volatile — check the current listing.

Check price on Amazon

Apple Mac Studio M4 Max

64 GB unified memory · 546 GB/s

2026 prices are volatile — check the current listing.

Check price on Amazon

No hardware? Rent the GPU first

Want to feel the 80B-A3B before committing to hardware? Rent a 48 GB+ instance for an hour and run it all-in-VRAM.

RunPod — RTX 4090 ≈ $0.3–0.7/hr, A100/H100 by the hour; serverless per-second billing available
Vast.ai — Marketplace of hosted GPUs — often the cheapest per hour (interruptible options)
Lambda — On-demand A100/H100/B200 instances and clusters, per-hour billing

Affiliate links — we may earn a commission if you sign up, at no extra cost to you.

Full list on the cloud AI directory.

Frequently asked questions

What hardware do I need to run Qwen3-Coder?

The 8B: any 8 GB GPU or 16 GB Mac (~6 GB at Q4). The 80B-A3B: ~49 GB all-in-VRAM — 2×24 GB GPUs or a 96 GB+ Mac — or ~8 GB VRAM + 32 GB system RAM with expert offload. The 480B-A35B: ~290 GB, i.e., multi-GPU servers or a hosted API.

Is Qwen3-Coder better than Qwen 2.5 Coder 32B?

Per parameter, yes — it is a generation newer. But the lineups don’t overlap cleanly: on a single 24 GB card, Qwen 2.5 Coder 32B (~20 GB) is still the bigger-brained dedicated coder you can fit, while Qwen3-Coder’s 8B wins the small tier and its 80B-A3B wins everything above 24 GB. Between tiers, benchmark both on your own code.

Can Qwen3-Coder be used commercially?

Yes — the whole family ships under Apache 2.0, with no non-production restrictions (unlike Codestral’s MNPL). You can run it for client work, inside a company, or embedded in a product.

Does Qwen3-Coder work for autocomplete (FIM)?

Yes — the family is fill-in-the-middle trained, and the 8B is fast enough on an 8 GB card to serve as the autocomplete model directly in Continue. On tighter VRAM or for the lowest latency, StarCoder2 3B remains the dedicated-sidecar option.