Qwen3-Coder 480B-A35B (MoE) — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The flagship dedicated coder: 480B total with 35B active parameters per token and 256K native context (extendable to ~1M). Holds state-of-the-art among open models on SWE-bench Verified and agentic coding at release, with Qwen positioning it comparable to Claude Sonnet 4. Datacenter / multi-GPU only — reach for the 80B-A3B when you need single-GPU deployment.
Qwen3-Coder 480B-A35B (MoE) needs about 291 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 159.6 GB | — | Too big | |
| Q3_K_M 3.41 bpw | 206.4 GB | — | Too big | |
| Q4_K_M 4.83 bpw | 291.6 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 342 GB | — | Too big | |
| Q6_K 6.56 bpw | 395.4 GB | — | Too big | |
| Q8_0 8.50 bpw | 511.8 GB | — | Too big | |
| F16 16.00 bpw | 961.8 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Qwen3-Coder 480B-A35B (MoE) VRAM calculator →
Get Qwen3-Coder 480B-A35B (MoE) running
The cheapest catalogued GPU that runs Qwen3-Coder 480B-A35B (MoE) is the Apple M3 Ultra (512 GB).
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Qwen3-Coder 480B-A35B (MoE)
Install Ollama, then run:
ollama run qwen3-coder:480b-a35bSpecifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 480 Billion (35B active)
- Context window
- 256,000
- Architecture
- Mixture-of-Experts
- Provider
- Alibaba Cloud
- Licence
- Apache 2.0
- Practical deployment
- Workstation (large unified memory or pro GPU)
- Specified at
- Q4_K_M
- System RAM
- 512 GB
- Record updated
- 2026-07-08
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| SWE-bench Verified | 69.6 % | reported · Qwen (open-model SoTA at release) |
Can I run Qwen3-Coder 480B-A35B (MoE) on my GPU?
- Qwen3-Coder 480B-A35B (MoE) on AMD Radeon RX 9060 XT 8GB
- Qwen3-Coder 480B-A35B (MoE) on AMD Ryzen AI Max+ 395
- Qwen3-Coder 480B-A35B (MoE) on Apple M2 Max
- Qwen3-Coder 480B-A35B (MoE) on Apple M3 Ultra
- Qwen3-Coder 480B-A35B (MoE) on Intel Arc B570
- Qwen3-Coder 480B-A35B (MoE) on Intel Arc B580
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA A100 80GB (PCIe)
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 3060 (12GB)
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 3070
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 3070 Ti
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 3080 (10GB)
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 4060
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 4070
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 4070 Super
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 4070 Ti
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 5060
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 5060 Ti 8GB
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA GeForce RTX 5070
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA H100 80GB (PCIe)
- Qwen3-Coder 480B-A35B (MoE) on NVIDIA RTX PRO 6000 Blackwell
Other Qwen3-Coder sizes
Qwen3-Coder 480B-A35B (MoE) — frequently asked questions
How much VRAM does Qwen3-Coder 480B-A35B (MoE) need?
About 291 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Qwen3-Coder 480B-A35B (MoE) run on an RTX 4090 (24 GB)?
No. Qwen3-Coder 480B-A35B (MoE) needs about 291 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Qwen3-Coder 480B-A35B (MoE) locally?
Install Ollama and run `ollama run qwen3-coder:480b-a35b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Qwen3-Coder come in?
Qwen3-Coder 8B (6 GB), Qwen3-Coder 30B-A3B (MoE) (19 GB), Qwen3-Coder-Next (80B-A3B MoE) (49 GB), Qwen3-Coder 480B-A35B (MoE) (291 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.