What are the hardware requirements for Qwen3 Coder 480B A35B Instruct 1M?

Qwen3 Coder 480B A35B Instruct 1M requires approximately 171.9 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 Coder 480B A35B Instruct 1M and how large is it?

Qwen3 Coder 480B A35B Instruct 1M is developed by unsloth, a model with 480b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3 Coder 480B A35B Instruct 1M?

Qwen3 Coder 480B A35B Instruct 1M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 Coder 480B A35B Instruct 1M by unsloth — VRAM 171.9GB, 1024K context

Name: Qwen3 Coder 480B A35B Instruct 1M
Author: unsloth

Qwen3 Coder 480B A35B Instruct 1M is an open-source language model by unsloth. Features: 480b LLM, VRAM: 171.9GB, Context: 1024K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.19.

Arxiv:2505.09388 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-coder-48... Codegen Conversational Endpoints compatible Instruct Qwen3 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-1M

Qwen3 Coder 480B A35B Instruct 1M Parameters and Internals

LLM Name	Qwen3 Coder 480B A35B Instruct 1M
Repository 🤗	https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-1M
Base Model(s)	Qwen3 Coder 480B A35B Instruct Qwen/Qwen3-Coder-480B-A35B-Instruct
Model Size	480b
Required VRAM	171.9 GB
Updated	2026-08-05
Maintainer	unsloth
Model Type	qwen3_moe
Instruction-Based	Yes
Model Files	4.0 GB: 1-of-241 4.0 GB: 2-of-241 4.0 GB: 3-of-241 4.0 GB: 4-of-241 4.0 GB: 5-of-241 4.0 GB: 6-of-241 4.0 GB: 7-of-241 4.0 GB: 8-of-241 4.0 GB: 9-of-241 4.0 GB: 10-of-241 4.0 GB: 11-of-241 4.0 GB: 12-of-241 4.0 GB: 13-of-241 4.0 GB: 14-of-241 4.0 GB: 15-of-241 3.9 GB: 16-of-241 4.0 GB: 17-of-241 4.0 GB: 18-of-241 4.0 GB: 19-of-241 4.0 GB: 20-of-241 4.0 GB: 21-of-241 4.0 GB: 22-of-241 4.0 GB: 23-of-241 4.0 GB: 24-of-241 4.0 GB: 25-of-241 4.0 GB: 26-of-241 4.0 GB: 27-of-241 4.0 GB: 28-of-241 4.0 GB: 29-of-241 4.0 GB: 30-of-241 4.0 GB: 31-of-241 4.0 GB: 32-of-241 4.0 GB: 33-of-241 4.0 GB: 34-of-241 4.0 GB: 35-of-241 4.0 GB: 36-of-241 4.0 GB: 37-of-241 4.0 GB: 38-of-241 4.0 GB: 39-of-241 4.0 GB: 40-of-241 4.0 GB: 41-of-241 4.0 GB: 42-of-241 4.0 GB: 43-of-241
Generates Code	Yes
Model Architecture	Qwen3MoeForCausalLM
License	apache-2.0
Context Length	1048576
Model Max Length	1048576
Transformers Version	4.53.3
Vocabulary Size	151936
Torch Data Type	bfloat16

Rank the Qwen3 Coder 480B A35B Instruct 1M capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen3 Coder 480B A35B Instruct 1M

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 Coder 480B A35B Instruct	256K / 167.9 GB	35	5
Qwen3 Coder 480B A35B Instruct	256K / 171.9 GB	29491	1356
...3 Coder 480B A35B Instruct FP8	256K / 429.8 GB	326683	159
...Coder 480B A35B Instruct NVFP4	256K / 210 GB	768	12
Qwen3 Coder REAP 363B A35B	256K / 215 GB	202	5
...3 Coder 480B A35B Instruct FP8	256K / 429.8 GB	59	8
... Coder 480B A35B Instruct 4bit	256K / 185.6 GB	2835	19

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-Coder-480B-A35B-Instruct-1M.