OpenModelStats

Qwen3.8-27B-MLX-6bit-MTPLX

tokenfires/Qwen3.8-27B-MLX-6bit-MTPLX

Text Generation27.4B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since September 9, 2026View on Hugging Face ↗
Downloads 30D
369
Total downloads
369
Gained 7D
0
Gained 30D
—
Likes
1
+0 in 7D
Rank · tracked models
#47,775
326(down 326 places)this week
Parameters
27.4B
Last source update
Aug 26, 2026
Momentum
4.4
  • It moved from #14220 to #14356 among tracked Text Generation models this week.
7D30D90D1YAll
Total downloadsGained per dayRolling recent downloads

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.8-27B-MLX-6bit-MTPLX is a text generation model published by tokenfires. OpenModelStats has tracked the model since Sep 9, 2026, most recently observing it Sep 2, 2026.

Published
Aug 26, 2026
Last updated
Aug 26, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
27,356,723,952
Spaces
—
Derivative models
—
Velocity 7D/day
0
mlxsafetensorsqwen3_5mtplxspeculative-decodingmulti-token-predictionapple-silicon6-bittext-generationconversationalenbase_model:Qwen/Qwen3.8-27B

Publisher

tokenfiresView publisher statistics →

Derived from Qwen/Qwen3.8-27B (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3.8-27B-MLX-6bit-MTPLX
ModelDL 30D
Qwen3.8-27B-MTPLX-Optimized-SpeedYoussofal28K
Qwen3.8-27B-MTPLX-Optimized-QualityYoussofal9,335
Qwen3.8-27B-MTPLX-Optimized-Speed-FP16Youssofal5,412
Qwen3.8-27B-MTPLX-Optimized-Quality-FP16Youssofal2,923
Qwen3.8-27B-MTPLX-Bare-Speed-FP16Youssofal2,209
Qwen3.8-27B-MTPLX-Bare-SpeedYoussofal2,157
tokenfires/Qwen3.8-27B-MLX-6bit-MTPLX — Downloads, Growth & Stats | OpenModelStats