Run Qwen3-Coder locally and use it from anywhere

Last verified: 2026-10-14

Qwen3-Coder is Qwen’s coding-focused open model family for agentic coding, repository-scale context, and tool-using development clients. Start with qwen3-coder:30b unless you have a very large unified-memory or multi-GPU system.

For the newer general Qwen line, see Qwen3.6 on Ollama. Its Ollama page lists 27b and 35b vision-capable, tool-capable tags with 256K context. This page stays focused on the legacy qwen3-coder family.

Variants and tags

Variant	Ollama tag	Architecture	Context	Default download	License	Sources
Practical local coder	`qwen3-coder:30b`	MoE, `30.5B` total and `3.3B` activated, `128` experts, `8` activated experts	`256K` native, extendable to `1M` with YaRN on the HF model card	`19GB`	Apache 2.0	Ollama Qwen3-Coder, Qwen/Qwen3-Coder-30B-A3B-Instruct
Large local tier	`qwen3-coder:480b`	Large MoE coder model	`256K`	`290GB`; Ollama states local running requires at least `250GB` memory or unified memory	Apache 2.0 on Qwen3-Coder cards	Ollama Qwen3-Coder, Qwen3-Coder blog
Hosted Ollama Cloud tier	`qwen3-coder:480b-cloud`	Cloud-served 480B tier	`256K`	Cloud tag, not a local weight download	Apache 2.0 on Qwen3-Coder cards	Ollama Qwen3-Coder

The 480b-cloud tag is not a local model download. Tokios is for connecting your own local runtime. Use the local 30b or 480b tags, or serve Hugging Face weights yourself, when you want a Tokios-backed deployment.

Quantization and formats

Ollama gives you the simplest GGUF path. Hugging Face provides the upstream safetensors checkpoint and links out to compatible quantized builds for llama.cpp, Ollama, LM Studio, and similar apps. See Quantization formats and the hardware they need before you choose a quant.

Format	Use it when	Hardware notes	Sources
Ollama `GGUF` tags	You want one-command local serving	`qwen3-coder:30b` is the practical single-workstation path; `480b` requires far more memory	Ollama Qwen3-Coder
Hugging Face `safetensors`	You want vLLM, SGLang, Transformers, or custom serving	Use GPU memory planning from your runtime; start with the 30B-A3B checkpoint unless you have multi-GPU capacity	Qwen/Qwen3-Coder-30B-A3B-Instruct
Other quant repos	You want a specific `Q4`, `Q5`, `Q8`, or full-precision file	Verify the exact repo and filename. Do not assume AWQ, GPTQ, or other formats exist for a tag until the repo lists them.	Qwen/Qwen3-Coder-30B-A3B-Instruct local apps section

Hardware fit

The 30b Ollama tag downloads at 19GB, so it fits many 24GB cards with careful context settings. The 480b tag downloads at 290GB, and Ollama says it needs at least 250GB memory or unified memory. Use Fit a model to your GPU or unified memory for the sizing method.

Target	`qwen3-coder:30b`	`qwen3-coder:480b`
RTX 3090 / 4090, `24GB`	Good starter fit at default Ollama quant; reduce context if you hit OOM	Won’t fit
RTX 5090, `32GB`	Comfortable for local coding experiments	Won’t fit
RTX 6000 Ada / A6000, `48GB`	Comfortable, with more context room	Won’t fit by itself
Apple MLX / unified memory, `36-128GB`	Fits on higher-memory systems; speed depends on bandwidth	Won’t fit below the memory class Ollama lists
AMD ROCm / Vulkan / Strix Halo	Depends on assignable GPU memory; the `30b` tag is the realistic target	Won’t fit unless the system exposes enough usable memory

Run it locally first

Ollama
LM Studio
Unsloth Studio
vLLM
SGLang

Pull the practical local tag:

ollama run qwen3-coder:30b

Check the Ollama Qwen3-Coder library page before using a larger tag.

Search for Qwen3-Coder or a compatible GGUF build, choose a quant that fits your memory, and start LM Studio’s local server at http://127.0.0.1:1234/v1.

Search for a Qwen3-Coder GGUF build in Unsloth Studio, load the quant that fits, and start its OpenAI-compatible server. See Use Unsloth Studio from anywhere for the Tokios setup.

The model card lists a direct vLLM launch:

vllm serve "Qwen/Qwen3-Coder-30B-A3B-Instruct"

Point Tokios at http://127.0.0.1:8000/v1. Source: Qwen/Qwen3-Coder-30B-A3B-Instruct.

The model card lists a direct SGLang launch:

python3 -m sglang.launch_server \
  --model-path "Qwen/Qwen3-Coder-30B-A3B-Instruct" \
  --host 127.0.0.1 \
  --port 30000

Point Tokios at http://127.0.0.1:30000/v1. Source: Qwen/Qwen3-Coder-30B-A3B-Instruct.

Capabilities

Capability	What to expect	Sources
Coding	Built for agentic coding, browser-use, and foundational coding tasks.	Qwen/Qwen3-Coder-30B-A3B-Instruct, Qwen3-Coder blog
Tool calling	The model card says Qwen3-Coder uses a specially designed function-call format and excels in tool calling. Ollama tags the family with `tools`.	Qwen/Qwen3-Coder-30B-A3B-Instruct, Ollama Qwen3-Coder
Long context	`256K` native on Ollama and HF; the HF card says the 30B-A3B model can extend to `1M` tokens with YaRN.	Ollama Qwen3-Coder, Qwen/Qwen3-Coder-30B-A3B-Instruct
Thinking mode	The 30B-A3B card says the model supports non-thinking mode only and does not generate `<think>` blocks.	Qwen/Qwen3-Coder-30B-A3B-Instruct
Vision	No. Use Qwen3-VL if your coding workflow needs images or screenshots.	Ollama Qwen3-VL

If you hit OOM with Hugging Face weights, Qwen’s model card recommends reducing context length, for example to 32,768.

Connect it with Tokios

Once Qwen3-Coder runs locally, pair the Tokios connector so Claude Code, Cline, and other clients can call it through https://api.tokios.com instead of only localhost.

Run Qwen3-Coder locally

Start with the local 30b tag:

ollama run qwen3-coder:30b

Pair the Tokios connector

Sign in at tokios.com/console, open Setup, and click Start pairing to get a one-time claim code shaped TKS-XXXX-XXXX.

macOS

curl -fsSL https://tokios.com/downloads/install/macos | sh -s -- --code TKS-XXXX-XXXX

Windows

irm https://tokios.com/downloads/install/windows | iex; tokios-install -Code 'TKS-XXXX-XXXX'

Linux

curl -fsSL https://tokios.com/downloads/install/linux | sh -s -- --code TKS-XXXX-XXXX

Approve the device in Setup or Connectors.

Set the upstream BaseUrl

For Ollama, point the connector at the /v1 API:

{
  "Upstream": {
    "BaseUrl": "http://127.0.0.1:11434/v1"
  }
}

For LM Studio use http://127.0.0.1:1234/v1, for vLLM use http://127.0.0.1:8000/v1, and for the SGLang command above use http://127.0.0.1:30000/v1.

In Models, register the upstream model and choose a deployment name such as qwen3-coder-tunnel.

Create an API key

In Keys, click Create key. Copy the sk-tok-YOUR_KEY value now because it is shown once.

curl https://api.tokios.com/v1/chat/completions \
  -H "Authorization: Bearer sk-tok-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-coder-tunnel",
    "stream": true,
    "messages": [{"role": "user", "content": "Write a TypeScript function that batches async work with a concurrency limit."}]
  }'

export ANTHROPIC_BASE_URL=https://api.tokios.com
export ANTHROPIC_API_KEY=sk-tok-YOUR_KEY
claude --model qwen3-coder-tunnel

The model field is always your registered deployment name, not qwen3-coder:30b or the Hugging Face model id.

Next steps

Quickstart

Pair a connector and register your first deployment end to end.

Use Claude Code

Point Claude Code at your Tokios deployment.

Fit a model to your GPU

Estimate whether the 30b or 480b tier fits your machine.

Quantization and hardware

Pick a format before you download a large quant.

Get Started

Models

Concepts

Reference

Run Qwen3-Coder locally and use it from anywhere

Variants and tags

Quantization and formats

Hardware fit

Run it locally first

Capabilities

Connect it with Tokios

Next steps

Quickstart

Use Claude Code

Fit a model to your GPU

Quantization and hardware

​Variants and tags

​Quantization and formats

​Hardware fit

​Run it locally first

​Capabilities

​Connect it with Tokios

​Next steps

Quickstart

Use Claude Code

Fit a model to your GPU

Quantization and hardware

Variants and tags

Quantization and formats

Hardware fit

Run it locally first

Capabilities

Connect it with Tokios

Next steps