Qwen / text-generation updated 11 months ago

Qwen3-Coder-480B-A35B-Instruct-FP8

Name: Qwen3-Coder-480B-A35B-Instruct-FP8
Author: Qwen

Today, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct. featuring the following key enhancements:

Params

480.2 B

Context

262,144

Downloads 30d

327 K

Likes

159

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

386 K301 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	482.1 GB	602.9 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	482.1 GB	2,835.7 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-coder-480b-a35b-instruct-fp8
{
  "hf_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
  "params_b": 480.18,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 326683,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 602.9 }
  ],
  "updated_at": "2026-07-28T18:05:56Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen3MoeForCausalLM
Parameters: 480.2 B
Tensor type: F8_E4M3
Context length: 262,144
Vocabulary: 151,936
Layers / heads: 62 / 96
Licence: apache-2.0
First seen on the Hub: 2025-07-22
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

DeepSeek-R1 9.9 M gpt-oss-120b 4.2 M DeepSeek-V4-Flash 2.7 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M GLM-5.2-NVFP4 1.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB