Alibaba/Dense

Qwen2.5-7B

Name: Qwen2.5-7B
Author: Alibaba

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.

chattool_use

7.6B

Parameters

32K

Context length

Benchmarks

Quantizations

20.5M

HF downloads

Architecture

Dense

Released

2024-09-16

Layers

KV Heads

Head Dim

128

Family

qwen

Quantization Options

Context length:

Quant	Bits	VRAM @ 16K	Quality
Q4_K_M	4.89	5.8 GB 5.1 + 0.7 KV	good
Q5_K_S	5.57	6.4 GB 5.8 + 0.7 KV	good
Q5_K_M	5.7	6.6 GB 5.9 + 0.7 KV	good
Q6_K	6.56	7.4 GB 6.7 + 0.7 KV	excellent
Q8_0	8.5	9.2 GB 8.6 + 0.7 KV	lossless
FP16	16	16.3 GB 15.7 + 0.7 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 QWEN2.5-7B 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 (11)

Arena Elo1460

IFEval75.9

MBPP60.8

MATH50.0

HumanEval45.7

MMLU-PRO36.5

BBH34.9

BigCodeBench29.1

MUSR8.5

GPQA5.5

GPQA Diamond5.5

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

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

$ollama run qwen2.5:7.6b

Tag may need adjustment — check ollama.com/library/qwen2.5 for available tags.

▸ 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.

NVIDIA RTX 3050 6GB

6 GB VRAM • 168 GB/s

NVIDIA

$169

QUANT	BPW	VRAM	QUALITY
Q4_K_M	4.89	5.1 GB	94%
Q5_K_S	5.57	5.8 GB	96%
Q5_K_M	5.7	5.9 GB	96%
Q6_K	6.56	6.7 GB	97%
Q8_0	8.5	8.6 GB	100%
FP16	16	15.7 GB	100%