Alibaba

Qwen 2.5 32B

Name: Qwen 2.5 32B
Author: Alibaba

Current

HuggingFace

Ollama

2.9MDownloads337LikesSep 2024Released131K tokensContextApache 2.0License4 EntryQuality

Get started

— copy & paste to run locally

Ollama

ollama run qwen-2.5-32b

HuggingFace

huggingface-cli download qwen-2.5-32b

Quick specs

Parameters32B

Architecturedense

Context131K tokens

Modalitytext

Min RAM12.5 GB

Rec. RAM19.5 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ Code✓ Chat✓ Reasoning

About this model

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

•Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models...
•Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g,...
•Long-context Support: up to 128K tokens and can generate up to 8K tokens
•Multilingual support: for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean,...

Related models

Quick picks

Best budgetC

Mac mini M4 64GB~$1,099 — 4 tok/s

Best overallB

NVIDIA A100 40GB~$10,000 — 67 tok/s

Best hardware

Top picks for Qwen 2.5 32B

NVIDIA A100 40GBB

40 GB

RTX PRO 5000 Blackwell 48GBC

Mac Studio M2 Ultra 64GBC

64 GB

Quantization options

VRAM estimates by quant level

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 2.5 32B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+88.4%

Aider Polyglot—

LiveCodeBench—

Reasoning

MMLU-Pro69.0%

GPQA Diamond49.5%

MATH-50083.1%

ARC Challenge—

General

Chatbot Arena—

IFEval79.5%

Source: official · 2024-09-19

Hardware compatibility

Fit estimates across all hardware

Open calculator

Computing compatibility...

Memory breakdown

Reference: NVIDIA A10 24GB

Weights19.5 GB

KV Cache5.0 GB

Runtime0.9 GB

Headroom2.4 GB

Quant

Bits

VRAM

Quality

Fit

Q2_K

12.5 GB

Low

—

Q3_K_S

15.7 GB

Low

—

NVFP4

17.9 GB

Medium

—

Q4_K_M

19.5 GB

Medium

—

Q5_K_M

23.0 GB

High

—

Q6_K

26.2 GB

High

—

Q8_0

34.2 GB

Very High

—

F16

65.6 GB

Maximum

—