Alibaba/Mixture of Experts

Qwen3-Next 80B A3B

Name: Qwen3-Next 80B A3B
Author: Alibaba

Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI).

chatcodingreasoningmultilingualtool_use

80B

Parameters (3B active)

256K

Context length

Benchmarks

Quantizations

Architecture

MoE

Released

2025-09-12

Layers

KV Heads

Head Dim

256

Family

qwen

Quantization Options

Context length:

Quant	Bits	VRAM @ 16K	Quality
IQ2_M	2.93	30.1 GB 29.8 + 0.3 KV	low
Q2_K	3.16	32.4 GB 32.1 + 0.3 KV	low
IQ3_XXS	3.25	33.3 GB 33.0 + 0.3 KV	low
IQ3_XS	3.5	35.8 GB 35.5 + 0.3 KV	low
Q3_K_S	3.64	37.2 GB 36.9 + 0.3 KV	low
IQ3_M	3.76	38.4 GB 38.1 + 0.3 KV	low
Q3_K_M	4	40.8 GB 40.5 + 0.3 KV	low
Q3_K_L	4.3	43.8 GB 43.5 + 0.3 KV	moderate
IQ4_XS	4.46	45.4 GB 45.1 + 0.3 KV	moderate
Q4_K_S	4.67	47.5 GB 47.2 + 0.3 KV	moderate
Q4_K_M	4.89	49.7 GB 49.4 + 0.3 KV	good
Q5_K_S	5.57	56.5 GB 56.2 + 0.3 KV	good
Q5_K_M	5.7	57.8 GB 57.5 + 0.3 KV	good
Q6_K	6.56	66.4 GB 66.1 + 0.3 KV	excellent
Q8_0	8.5	85.8 GB 85.5 + 0.3 KV	lossless
FP16	16	160.8 GB 160.5 + 0.3 KV	lossless

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

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN QWEN3-NEXT 80B A3B NOW

Rent on Vast.ai →Or RunPod →

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

Community Ratings

Loading ratings...

Benchmarks (20)

IFEval85.9

AIME84.3

AA Math84.3

LiveCodeBench78.4

GPQA Diamond75.9

MATH-50066.3

IFBench60.7

BBH60.5

AA Long Context60.3

MATH60.1

MMLU-PRO50.4

τ²-Bench41.5

SciCode38.8

BigCodeBench33.2

AA Intelligence26.7

AA Coding19.5

GPQA19.4

MUSR12.3

HLE11.7

Terminal-Bench9.8

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run qwen3-next:80b-a3b-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

HuggingFace Ollama Library GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M1 Ultra (64GB)

64 GB VRAM • 800 GB/s

APPLE

$2499

Apple M2 Ultra (64GB)

64 GB VRAM • 800 GB/s

APPLE

$2999

Apple M4 Max (64GB)

64 GB VRAM • 546 GB/s

APPLE

$2899

Apple M2 Max (64GB)

64 GB VRAM • 400 GB/s

APPLE

$2299

Apple M3 Max (64GB)

64 GB VRAM • 300 GB/s

APPLE

$2799

Apple M4 Pro (64GB)

64 GB VRAM • 273 GB/s

APPLE

$2599

AMD Radeon Instinct MI200

64 GB VRAM • 1640 GB/s

AMD

$10000

AMD Radeon Instinct MI210

64 GB VRAM • 1640 GB/s

AMD

$8000

NVIDIA H100 SXM5 64 GB

64 GB VRAM • 2020 GB/s

NVIDIA

$25000

NVIDIA Jetson AGX Orin 64 GB

64 GB VRAM • 205 GB/s

NVIDIA

NVIDIA Jetson T4000

64 GB VRAM • 273 GB/s

NVIDIA

Apple M5 Pro (64GB)

64 GB VRAM • 200 GB/s

APPLE

Apple M5 Max (64GB)

64 GB VRAM • 614 GB/s

APPLE

NVIDIA RTX PRO 5000 72 GB Blackwell

72 GB VRAM • 1340 GB/s

NVIDIA

$6999

NVIDIA H100 SXM5 80GB

80 GB VRAM • 3350 GB/s

NVIDIA

$25000

NVIDIA H100 PCIe 80GB

80 GB VRAM • 2000 GB/s

NVIDIA

$25000

NVIDIA A100 SXM 80GB

80 GB VRAM • 2039 GB/s

NVIDIA

$10000

NVIDIA A100 PCIe 80GB

80 GB VRAM • 1935 GB/s

NVIDIA

$10000

NVIDIA A100 SXM4 80 GB

80 GB VRAM • 2040 GB/s

NVIDIA

$15000

NVIDIA A100 PCIe 80 GB

80 GB VRAM • 1940 GB/s

NVIDIA

$10000

NVIDIA A100X

80 GB VRAM • 2040 GB/s

NVIDIA

NVIDIA H100 PCIe 80 GB

80 GB VRAM • 2040 GB/s

NVIDIA

$25000

NVIDIA H100 SXM5 80 GB

80 GB VRAM • 3360 GB/s

NVIDIA

$25000

NVIDIA H100 CNX

80 GB VRAM • 2040 GB/s

NVIDIA

$25000

NVIDIA A800 PCIe 80 GB

80 GB VRAM • 1940 GB/s

NVIDIA

NVIDIA A800 SXM4 80 GB

80 GB VRAM • 2040 GB/s

NVIDIA

NVIDIA H800 PCIe 80 GB

80 GB VRAM • 2040 GB/s

NVIDIA

NVIDIA H800 SXM5

80 GB VRAM • 3360 GB/s

NVIDIA

NVIDIA RTX 6000D

84 GB VRAM • 1570 GB/s

NVIDIA

$7500

NVIDIA B200

90 GB VRAM • 4100 GB/s

NVIDIA

$30000

Find the best GPU for Qwen3-Next 80B A3B

Build Hardware for Qwen3-Next 80B A3B

QUANT	BPW	VRAM	QUALITY
IQ2_M	2.93	29.8 GB	75%
Q2_K	3.16	32.1 GB	78%
IQ3_XXS	3.25	33.0 GB	82%
IQ3_XS	3.5	35.5 GB	84%
Q3_K_S	3.64	36.9 GB	85%
IQ3_M	3.76	38.1 GB	86%
Q3_K_M	4	40.5 GB	88%
Q3_K_L	4.3	43.5 GB	90%
IQ4_XS	4.46	45.1 GB	92%
Q4_K_S	4.67	47.2 GB	93%
Q4_K_M	4.89	49.4 GB	94%
Q5_K_S	5.57	56.2 GB	96%
Q5_K_M	5.7	57.5 GB	96%
Q6_K	6.56	66.1 GB	97%
Q8_0	8.5	85.5 GB	100%
FP16	16	160.5 GB	100%

Qwen3-Next 80B A3B

Quantization Options

Community Ratings

Benchmarks (20)

Run this model

Auto-setup with fitmyllm CLI

GPUs that can run this model

Qwen3-Next 80B A3B — 80B MoE.