Alibaba

Qwen 2.5 7B

Name: Qwen 2.5 7B
Rating: 75 (193 reviews)
Author: Alibaba

Atual

HuggingFace

Ollama

12.9MDownloads1.3KCurtidasSep 2024Publicado131K tokensContextoApache 2.0Licença62 BomQualidade

Qwen 2.5 7B (7B parameters) requires approximately 6.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 8 GB of VRAM.

Comece agora

— copie e cole para rodar localmente

Copy-paste commands to run Qwen 2.5 7B on your machine.

Run

ollama run qwen2.5

Quick specs

Parameters7B

Architecturedense

Context131K tokens

Modalitytext

Min RAM2.7 GB

Rec. RAM4.3 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ Chat

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,...

Modelos relacionados

Escolhas rápidas

Melhor custo-benefícioA

Intel Arc A580 8GB~$179 — 64 tok/s

Melhor no geralA

RTX 3080 10GB~$699 — 98 tok/s

Melhor hardware

Melhores opções para Qwen 2.5 7B

Rodar este modelo

Qwen 2.5 7B on RTX 3080 10GB Qwen 2.5 7B on RTX 2080 Ti 11GB Qwen 2.5 7B on GTX 1080 Ti 11GB

Opções de quantização

Estimativas de VRAM por nível de quantização

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	—
Q3_K_S	3	3.4 GB	Low	—
NVFP4	4	3.9 GB	Medium	—
Q4_K_M	4	4.3 GB	Medium	—
Q5_K_M	5	5.0 GB	High	—
Q6_K	6	5.7 GB	High	—
Q8_0	8	7.5 GB	Very High	—
F16	16	14.3 GB	Maximum	—

Quality benchmarks

Qwen 2.5 7B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+84.8%

Aider Polyglot—

LiveCodeBench28.7%

Reasoning

MMLU-Pro56.3%

GPQA Diamond36.4%

MATH-50075.5%

ARC Challenge—

General

Chatbot Arena—

IFEval71.2%

Source: official · 2024-09-19

Compatibilidade de hardware

Estimativas de compatibilidade para todo o hardware

Abrir calculadora

Computing compatibility...

Detalhamento de memória

Reference: RTX 2060 6GB

Weights4.3 GB

KV Cache0.9 GB

Runtime0.9 GB

Headroom0.6 GB

Perguntas frequentes

FAQ — Qwen 2.5 7B

Veja também

Guia de Quantização Metodologia de Pontuação Abrir calculadora