FitMyLLM
Alibaba/Mixture of Experts

AlibabaQwen3-Coder-480B-A35B

chattool_usecoding
480.2B
Parameters (35B active)
256K
Context length
15
Benchmarks
17
Quantizations
87K
HF downloads
Architecture
MoE
Released
2025-11-01
Layers
62
KV Heads
8
Head Dim
128
Family
qwen

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.38143.3 GBlow
IQ2_M2.93176.4 GBlow
Q2_K3.16190.2 GBlow
IQ3_XXS3.25195.6 GBlow
IQ3_XS3.5210.6 GBlow
Q3_K_S3.64219.0 GBlow
IQ3_M3.76226.2 GBlow
Q3_K_M4240.6 GBlow
Q3_K_L4.3258.6 GBmoderate
IQ4_XS4.46268.2 GBmoderate
Q4_K_S4.67280.8 GBmoderate
Q4_K_M4.89294.0 GBgood
Q5_K_S5.57334.8 GBgood
Q5_K_M5.7342.6 GBgood
Q6_K6.56394.3 GBexcellent
Q8_08.5510.7 GBlossless
FP1616960.9 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN QWEN3-CODER-480B-A35B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (15)

MATH-50094.2
MMLU-PRO78.8
SWE-bench69.6
GPQA Diamond61.8
LiveCodeBench58.5
τ²-Bench43.6
AA Long Context42.3
IFBench40.5
AIME39.3
AA Math39.3
SciCode35.9
AA Intelligence24.8
AA Coding24.6
Terminal-Bench18.9
HLE4.4

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run qwen3:480.2b-instruct-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M4 Ultra (384GB)
384 GB VRAM • 1092 GB/s
APPLE
$9999
Apple M5 Ultra (384GB)
384 GB VRAM • 1228 GB/s
APPLE

Find the best GPU for Qwen3-Coder-480B-A35B

Build Hardware for Qwen3-Coder-480B-A35B
▸ SPEC SHEET

Qwen3-Coder-480B-A35B — 480.2B MoE.

▸ SPECIFICATIONS
PARAMETERS
480.2B (35B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
256K tokens
CAPABILITIES
chat, tool_use, coding
RELEASE DATE
2025-11-01
PROVIDER
Alibaba
FAMILY
qwen
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.38143.3 GB65%
IQ2_M2.93176.4 GB75%
Q2_K3.16190.2 GB78%
IQ3_XXS3.25195.6 GB82%
IQ3_XS3.5210.6 GB84%
Q3_K_S3.64219.0 GB85%
IQ3_M3.76226.2 GB86%
Q3_K_M4240.6 GB88%
Q3_K_L4.3258.6 GB90%
IQ4_XS4.46268.2 GB92%
Q4_K_S4.67280.8 GB93%
Q4_K_M4.89294.0 GB94%
Q5_K_S5.57334.8 GB96%
Q5_K_M5.7342.6 GB96%
Q6_K6.56394.3 GB97%
Q8_08.5510.7 GB100%
FP1616960.9 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO78.8
LiveCodeBench58.5
SWE-bench69.6
AIME39.3
MATH-50094.2
GPQA Diamond61.8
HLE4.4
AA Intelligence24.8
AA Coding24.6
AA Math39.3
aa_ifbench40.5
aa_terminal_bench18.9
aa_tau243.6
aa_scicode35.9
aa_lcr42.3
§ 02RUN COMMAND

Run Qwen3-Coder-480B-A35B locally with Ollama — needs 294.0 GB VRAM at Q4_K_M:

$ollama run qwen3:480.2b
§ 03COMPATIBLE GPUs
2 @ Q4_K_M
Apple M4 Ultra (384GB)
384 GB · 1092 GB/s
Apple M5 Ultra (384GB)
384 GB · 1228 GB/s