How much VRAM does Qwen 3 Coder 480B-A35B (MoE) need?

Qwen 3 Coder 480B-A35B (MoE) requires approximately 0.0 GB VRAM at Q4_K_M quantization with 1K context and 10% overhead. At Q8_0 it needs ~0.0 GB, and at FP16 ~0.0 GB. Use the PCPARTGUIDE VRAM Calculator for exact requirements at any context length and overhead setting.

Can I run Qwen 3 Coder 480B-A35B (MoE) on a consumer GPU?

Qwen 3 Coder 480B-A35B (MoE) is a 480B parameter model and requires datacenter or multi-GPU setups. At Q4_K_M, it needs approximately 0.0 GB VRAM, which exceeds consumer GPU limits. It can run on H100 (80 GB) or A100 (80 GB) datacenter GPUs, or across multiple consumer GPUs with tensor parallelism.

What is Qwen 3 Coder 480B-A35B (MoE)'s context window?

Qwen 3 Coder 480B-A35B (MoE) supports a maximum context window of 262,144 tokens. The default context is 32,768 tokens. Larger contexts require proportionally more VRAM for the KV cache — use the VRAM Calculator to estimate exact requirements at your target context length.

What quantization level should I use for Qwen 3 Coder 480B-A35B (MoE)?

For Qwen 3 Coder 480B-A35B (MoE), start with Q4_K_M (~0.0 GB) if VRAM-limited. Q8_0 offers better quality at ~2× the VRAM. If you have enough VRAM, Q6_K (~1.5× Q4 VRAM) provides a good balance. For models this large, Q3_K_M may be necessary to fit on consumer hardware.

How does Qwen 3 Coder 480B-A35B (MoE) compare to similar models?

Qwen 3 Coder 480B-A35B (MoE) is a 480.0B MoE model from the Qwen family. Browse other Qwen models on the PCPARTGUIDE directory for comparable alternatives with different parameter counts and VRAM requirements. Use the Model Transparency scores to assess documentation quality and reproducibility.

QwenMoEApache 2.0

Qwen 3 Coder 480B-A35B (MoE)

480.0B

Parameters

35.0B

Active

256K

Max Context

MoE

Architecture

—

Released

Text

Modality

About Qwen 3 Coder 480B-A35B (MoE)

Qwen 3 Coder 480B-A35B (MoE) is a mixture-of-experts (MoE) transformer language model from the Qwen family, containing 480B parameters across 96 layers. It has 480B total parameters loaded into VRAM with 35B active per token. It supports up to 262K tokens of context with a hidden dimension of 8192 and 8 KV heads for efficient grouped-query attention (GQA). Apache 2.0. Agentic coding MoE. Up to 1M extrapolated ctx. Server class.

CodeAgentic

Technical Specifications

Total Parameters480.0B

Active Parameters35.0B per token

ArchitectureMixture of Experts

Total Experts35

Attention TypeGQA (MoE)

Hidden Dimensiond = 8,192

Transformer Layers96

Attention Heads64

KV Headsn_kv = 8

Head Dimensiond_head = 128

Activation FunctionSwiGLU

NormalizationRMSNorm

Position EmbeddingRoPE

System Requirements

Estimated VRAM at 10% overhead for different quantization methods and context sizes.

Quantization	1K ctx	195K ctx	256K ctx
Q4_K_M0.50 B/W ~97% of FP16	248.5Cluster / Multi-GPU	321.3Cluster / Multi-GPU	344.1Cluster / Multi-GPU
Q8_01.00 B/W ~100% of FP16	496.6Cluster / Multi-GPU	569.5Cluster / Multi-GPU	592.2Cluster / Multi-GPU
F162.00 B/W Reference	992.8Cluster / Multi-GPU	1065.7Cluster / Multi-GPU	1088.4Cluster / Multi-GPU

Use the interactive VRAM Calculator to see exactly how much memory you need at any quantization level, context length, and overhead setting.

Open VRAM Calculator Best GPU Guide VRAM Guide