Alibaba

Qwen 3 32B

Name: Qwen 3 32B
Rating: 88 (81 reviews)
Author: Alibaba

最先端

HuggingFace

Ollama

5.1Mダウンロード697いいねApr 2025公開日131K トークンコンテキストApache 2.0ライセンス95 卓越品質

Qwen 3 32B (32B parameters) requires approximately 25.2 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 29 GB of VRAM.

はじめに

— コピー&ペーストでローカル実行

Copy-paste commands to run Qwen 3 32B on your machine.

Run

ollama run qwen3:32b

Quick specs

Parameters32B

Architecturedense

Context131K tokens

Modalitytext

Min RAM12.5 GB

Rec. RAM19.5 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ Chat✓ Reasoning

About this model

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:

•Uniquely support of seamless switching between thinking mode: (for complex logical reasoning, math, and coding) and non-thinking mode (for...
•Significantly enhancement in its reasoning capabilities: , surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking...
•Superior human preference alignment: , excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a...
•Expertise in agent capabilities: , enabling precise integration with external tools in both thinking and unthinking modes and achieving leading...
•Support of 100+ languages and dialects: with strong capabilities for multilingual instruction following and translation

Qwen 3 32Bのおすすめ

NVIDIA A100 40GBS

40 GB

RTX PRO 5000 Blackwell 48GBS

48 GB

MacBook Pro M4 Max 64GBS

このモデルを実行

Qwen 3 32B on NVIDIA A100 40GB Qwen 3 32B on RTX PRO 5000 Blackwell 48GB Qwen 3 32B on MacBook Pro M4 Max 64GB

量子化オプション

量子化レベル別VRAM推定値

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.5 GB	Low	—
Q3_K_S	3	15.7 GB	Low	—
NVFP4	4	17.9 GB	Medium	—
Q4_K_M	4	19.5 GB	Medium	—
Q5_K_M	5	23.0 GB	High	—
Q6_K	6	26.2 GB	High	—
Q8_0	8	34.2 GB	Very High	—
F16	16	65.6 GB	Maximum	—

Quality benchmarks

Qwen 3 32B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+—

Aider Polyglot—

LiveCodeBench65.7%

Reasoning

MMLU-Pro—

GPQA Diamond68.4%

MATH-50097.2%

ARC Challenge—

General

Chatbot Arena—

IFEval85.0%

Source: official · 2025-05-15

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights19.5 GB

KV Cache3.9 GB

Runtime1.2 GB

Headroom0.6 GB

よくある質問