15.7K Downloads

qwen2.5-coder-32b

Public

Description

32B version of the code-specific Qwen 2.5 for code generation, code reasoning and code fixing.

Use cases

Minimum system memory

19GB

Qwen2.5 Coder 32B by qwen

Context length up to 128k with rope settings yarn with a 4.0 factor (original context length 32k)

Trained on a source of 5.5 trillion tokens

This is a BASE model, and as such should be used for completion and generation, not chatting or instruct

Sources

The underlying model files this model uses

Based on

GGUF

MLX

MLX