Alibaba

Qwen 2.5 72B

Name: Qwen 2.5 72B
Author: Alibaba

Current

HuggingFace

Ollama

738.4KDownloads918LikesSep 2024Released131K tokensContextApache 2.0License5 EntryQuality

Get started

— copy & paste to run locally

Ollama

ollama run qwen-2.5-72b

HuggingFace

huggingface-cli download qwen-2.5-72b

Quick specs

Parameters72B

Architecturedense

Context131K tokens

Modalitytext

Min RAM28.1 GB

Rec. RAM43.9 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ 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

MacBook Pro M3 Max 128GB~$2,499 — 6 tok/s

Best overallB

NVIDIA H100 80GB~$40,000 — 64 tok/s

Best hardware

Top picks for Qwen 2.5 72B

Quantization options

VRAM estimates by quant level

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	28.1 GB	Low	—
Q3_K_S	3	35.3 GB	Low	—
NVFP4	4	40.3 GB	Medium	—
Q4_K_M	4	43.9 GB	Medium	—
Q5_K_M	5	51.8 GB	High	—
Q6_K	6	59.0 GB	High	—
Q8_0	8	77.0 GB	Very High	—
F16	16	147.6 GB	Maximum	—

Quality benchmarks

Qwen 2.5 72B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+86.6%

Aider Polyglot—

LiveCodeBench—

Reasoning

MMLU-Pro71.1%

GPQA Diamond49.0%

MATH-50083.1%

ARC Challenge—

General

Chatbot Arena—

IFEval84.1%

Source: official · 2024-09-19

Hardware compatibility

Fit estimates across all hardware

Open calculator

Computing compatibility...

Memory breakdown

Reference: NVIDIA A10 24GB

Weights43.9 GB

KV Cache11.3 GB

Runtime0.9 GB

Headroom2.4 GB

Quant

Bits

VRAM

Quality

Fit

Q2_K

28.1 GB

Low

—

Q3_K_S

35.3 GB

Low

—

NVFP4

40.3 GB

Medium

—

Q4_K_M

43.9 GB

Medium

—

Q5_K_M

51.8 GB

High

—

Q6_K

59.0 GB

High

—

Q8_0

77.0 GB

Very High

—

F16

147.6 GB

Maximum

—