Qwen3-14B-8bit

mlx-community/Qwen3-14B-8bit

Text Generation4.2B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since August 28, 2026View on Hugging Face ↗
Downloads 30D
1,227
Total downloads
5,536
Gained 7D
Gained 30D
Likes
0
Rank · tracked models
#24,729
169(up 169 places)this week
Parameters
4.2B
Last source update
Apr 28, 2025
  • It moved from #6919 to #6838 among tracked Text Generation models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-14B-8bit is a text generation model published by mlx-community. OpenModelStats has tracked the model since Aug 28, 2026, most recently observing it 5h ago.

Published
Apr 28, 2025
Last updated
Apr 28, 2025
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
4,153,891,840
Spaces
Derivative models
Velocity 7D/day
mlxsafetensorsqwen3text-generationconversationalbase_model:Qwen/Qwen3-14Bbase_model:quantized:Qwen/Qwen3-14Blicense:apache-2.08-bitregion:us

Publisher

mlx-communityView publisher statistics →

Derived from Qwen/Qwen3-14B (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-14B-8bit
ModelDL 30D
Qwen3-14B-MLX-8bitlmstudio-community64.8K
MagenticBrain-8bitmlx-community117
Qwen2.5-Coder-14B-Instruct-MLX-8bitlmstudio-community108K
Qwen2.5-14B-Instruct-MLX-8bitlmstudio-community2,207
Qwen2.5-Coder-14B-Instruct-8bitmlx-community1,587
granite-switch-4.1-3b-previewibm-granite2,136
mlx-community/Qwen3-14B-8bit — Downloads, Growth & Stats | OpenModelStats