Sobre

Qwen2.5-Coder-7B-Instruct is a 7B parameter instruction-tuned language model optimized for code-related tasks such as code generation, reasoning, and bug fixing. Based on the Qwen2.5 architecture, it incorporates enhancements like RoPE,...

Modelos Relacionados

Qwen: Qwen3.5 Plus 2026-04-202026-04-27 Qwen: Qwen3.6 Flash2026-04-27 Qwen: Qwen3.6 Max Preview2026-04-27 Qwen3.6 27B (Non-reasoning)2026-04-22 Qwen3.6 27B2026-04-21 Qwen3.6 Max Preview2026-04-20 Qwen3.6 35B A3B (Non-reasoning)2026-04-16 Qwen3.6 35B A3B2026-04-15

Benchmarks

MMLU-Pro

47.3%

GPQA Diamond

33.9%

HLE

4.8%

LiveCodeBench

12.6%

SciCode

14.8%

TerminalBench HardNão avaliado

MATH-500

66.0%

AIME

5.3%

AIME 2025Não avaliado

IFBenchNão avaliado

Long Context RecallNão avaliado

Tau2Não avaliado

Média do MercadoMelhor Score

Open Source

HuggingFace

apache-2.07BGGUF / GPTQ / AWQ

Downloads

2.3M

Curtidas

705

VRAM (FP16)

8-16 GB

GPU

RTX 4070 / M2 Pro

Qwen2.5 Coder 7B Instruct

Sobre

Modelos Relacionados

Preços

Calculadora de Custo

vs. Modelos Similares

Desempenho

Benchmarks

Open Source

Comparação Rápida

Modelos Similares