Alibaba

Qwen 2.5 Coder 32B

Name: Qwen 2.5 Coder 32B
Rating: 75 (81 reviews)
Author: Alibaba

Actual

HuggingFace

Ollama

1.1MDescargas2.0KMe gustaNov 2024Publicado131K tokensContextoApache 2.0Licencia66 BuenoCalidad

Qwen 2.5 Coder 32B (32B parameters) requires approximately 25.2 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 29 GB of VRAM.

Comenzar

— copia y pega para ejecutar en local

Copy-paste commands to run Qwen 2.5 Coder 32B on your machine.

Run

ollama run qwen2.5-coder

Quick specs

Parameters32B

Architecturedense

Context131K tokens

Modalitytext

Min RAM12.5 GB

Rec. RAM19.5 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ Code

About this model

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

•Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training...
•A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining...
•Long-context Support: up to 128K tokens

Modelos relacionados

Selecciones rápidas

Mejor económicoA

Mac mini M4 64GB~$1,099 — 9 tok/s

Mejor en generalA

NVIDIA A100 40GB~$10,000 — 72 tok/s

Mejor hardware

Mejores opciones para Qwen 2.5 Coder 32B

NVIDIA A100 40GBA

40 GB

RTX PRO 5000 Blackwell 48GBA

48 GB

MacBook Pro M4 Max 64GBA

Ejecutar este modelo

Qwen 2.5 Coder 32B on NVIDIA A100 40GB Qwen 2.5 Coder 32B on RTX PRO 5000 Blackwell 48GB Qwen 2.5 Coder 32B on MacBook Pro M4 Max 64GB

Opciones de cuantización

Estimaciones de VRAM por nivel de cuantización

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 Coder 32B benchmark scores

Benchmark verified

Coding

SWE-bench Verified41.0%

HumanEval+87.2%

Aider Polyglot—

LiveCodeBench31.4%

Reasoning

MMLU-Pro62.3%

GPQA Diamond41.8%

MATH-50076.4%

ARC Challenge—

General

Chatbot Arena—

IFEval79.9%

Source: official · 2024-11-12

Compatibilidad de hardware

Estimaciones de encaje en todo el hardware

Abrir calculadora

Computing compatibility...

Desglose de memoria

Reference: RTX 2060 6GB

Weights19.5 GB

KV Cache3.9 GB

Runtime1.2 GB

Headroom0.6 GB

Preguntas frecuentes

FAQ — Qwen 2.5 Coder 32B

Ver también

Guía de cuantización Metodología de puntuación Abrir calculadora