Qwen2.5-Coder-14B-Instruct-mlx-4bit

rao-studios/Qwen2.5-Coder-14B-Instruct-mlx-4bit

Text Generation14.8B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since October 26, 2026View on Hugging Face ↗
Downloads 30D
48
Total downloads
48
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
14.8B
Last source update
Oct 26, 2026

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-26. Charts appear as daily observations accumulate.

Overview

Qwen2.5-Coder-14B-Instruct-mlx-4bit is a text generation model published by rao-studios. OpenModelStats has tracked the model since Oct 26, 2026, most recently observing it Oct 27, 2026.

Published
Oct 26, 2026
Last updated
Oct 26, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
14,770,033,664
Spaces
—
Derivative models
—
Velocity 7D/day
—
mlxsafetensorsqwen2codemirrortext-generationconversationalbase_model:mlx-community/Qwen2.5-Coder-14B-Instruct-4bitbase_model:quantized:mlx-community/Qwen2.5-Coder-14B-Instruct-4bitlicense:apache-2.04-bitregion:us

Publisher

rao-studiosView publisher statistics →

Derived from mlx-community/Qwen2.5-Coder-14B-Instruct-4bit (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen2.5-Coder-14B-Instruct-mlx-4bit
ModelDL 30D
Qwen2.5-Coder-14B-InstructQwen1.8M
Qwen2.5-14B-Instruct-AWQQwen1.1M
Qwen2.5-14B-InstructQwen626.2K
Qwen2.5-Coder-14B-Instruct-AWQQwen220.2K
Qwen2.5-14B-Instruct-1MQwen153.4K
DeepSeek-R1-Distill-Qwen-14Bdeepseek-ai150.5K
rao-studios/Qwen2.5-Coder-14B-Instruct-mlx-4bit — Downloads, Growth & Stats | OpenModelStats