Qwen3.8-27B-UD-Q3_K_XL-DFlash2-MLX

nathansutton/Qwen3.8-27B-UD-Q3_K_XL-DFlash2-MLX

Text Generation26.9B parametersmlx
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
3,179
Total downloads
8,104
Gained 7D
+825(increase)
14.0%(up) vs baseline
Gained 30D
—
Likes
4
+1 in 7D
Rank · tracked models
#15,567
143(down 143 places)this week
Parameters
26.9B
Last source update
Aug 23, 2026
Momentum
83.0
  • Qwen3.8-27B-UD-Q3_K_XL-DFlash2-MLX gained 825 downloads during the last seven tracked days.
  • It moved from #3968 to #4016 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

Qwen3.8-27B-UD-Q3_K_XL-DFlash2-MLX is a text generation model published by nathansutton. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 32h ago.

Published
Aug 21, 2026
Last updated
Aug 23, 2026
Library
mlx
License
—
Task
Text Generation
Parameters
26,895,993,856
Spaces
—
Derivative models
—
Velocity 7D/day
118
mlxsafetensorsqwen3_5apple-siliconcodingunsloth-style-dynamic-quantspeculative-decodingtext-generationconversationalarxiv:2602.06036base_model:Qwen/Qwen3.8-27Bbase_model:quantized:Qwen/Qwen3.8-27B

Publisher

nathansuttonView publisher statistics →

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

Similar models

Models similar to Qwen3.8-27B-UD-Q3_K_XL-DFlash2-MLX
ModelDL 30D
Qwen3.8-27B-Uncensored-OptiQ-4bitmlx-community15.2K
Qwen3.8-27B-Abliterated-MTPLX-Optimized-SpeedPocketAiHub6,598
Qwen3.8-27B-3bit-MLX-TextOnlylukaskremla4,051
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-4bit-MLXchoppedgarlic3,515
Qwen-Qwen3.8-27B-MTPLXben01123,167
Qwen3.6-27B-OptiQ-4bitmlx-community2,774
nathansutton/Qwen3.8-27B-UD-Q3_K_XL-DFlash2-MLX — Downloads, Growth & Stats | OpenModelStats