Qwen3.8-2.4T-A95B-MLX-reap75-4bit

pipenetwork/Qwen3.8-2.4T-A95B-MLX-reap75-4bit

Text Generation641B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
571
Total downloads
6,963
Gained 7D
+87(increase)
1.3%(up) vs baseline
Gained 30D
—
Likes
2
+0 in 7D
Rank · tracked models
#38,141
829(down 829 places)this week
Parameters
641B
Last source update
Aug 13, 2026
Momentum
34.3
  • Qwen3.8-2.4T-A95B-MLX-reap75-4bit gained 87 downloads during the last seven tracked days.
  • It moved from #10205 to #10527 among tracked Text Generation models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.8-2.4T-A95B-MLX-reap75-4bit is a text generation model published by pipenetwork. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 2, 2026.

Published
Aug 13, 2026
Last updated
Aug 13, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
641,398,830,464
Spaces
0
Derivative models
—
Velocity 7D/day
12
mlxsafetensorsqwen3_5_moe_textapple-siliconmoe4-bitreapprunedtext-generationconversationalbase_model:Qwen/Qwen3.8-2.4T-A95Bbase_model:quantized:Qwen/Qwen3.8-2.4T-A95B

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

Models similar to Qwen3.8-2.4T-A95B-MLX-reap75-4bit
ModelDL 30D
Kimi-K2.5-P48NVFP4-MOESQISTA-DASLab0
Kimi-K3-Q2_K-t158-MTPLXOpensourceWTF633
GLM-5.3-Nota-NVFP4-Global-Pruned-17.75nota-ai614
cogito-671b-v2.1deepcogito542
DeepSeek-V3.1-4bitmlx-community1,337
DeepSeek-V3-0324-4bitmlx-community1,321
pipenetwork/Qwen3.8-2.4T-A95B-MLX-reap75-4bit — Downloads, Growth & Stats | OpenModelStats