qwen25-coder-14b

Public

Forked from qwen/qwen2.5-coder-14b

Model
Revisions

14B version of the code-specific Qwen 2.5 for code generation, code reasoning and code fixing.

Capabilities

Minimum system memory

8GB

Tags

14B
qwen2

Last updated

Updated 12 days agoby
sunny2026
Report

README

Qwen2.5 Coder 14B Instruct by qwen

Long-context Support up to 128K tokens with yarn rope scaling factor of 4.0

Designed for use with Code Agents

Up to 5.5 trillion training tokens including source code, text-code grounding, and synthetic data

Sources

The underlying model files this model uses

Based on

🤗lmstudio-community/Qwen2.5-Coder-14B-Instruct-GGUF→

GGUF

🤗lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-4bit→

MLX

🤗lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-8bit→

MLX