Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-6.8bpw

xpashkin/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-6.8bpw

Text Generation135B parametersmlx-serveLicense: other
Tracked by OpenModelStats since October 19, 2026View on Hugging Face ↗
Downloads 30D
152
Total downloads
152
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
135B
Last source update
Oct 17, 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 2026-10-19. Charts appear as daily observations accumulate.

Overview

Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-6.8bpw is a text generation model published by xpashkin. OpenModelStats has tracked the model since Oct 19, 2026, most recently observing it Oct 18, 2026.

Published
Oct 17, 2026
Last updated
Oct 17, 2026
Library
mlx-serve
License
other
Task
Text Generation
Parameters
134,950,835,462
Spaces
—
Derivative models
—
Velocity 7D/day
—
mlx-servesafetensorsqwen4_expmlxmoesparse-attentionngram-embeddingimatrixtext-generationconversationalbase_model:Qwen/Qwen3.8-Flash-Nextbase_model:quantized:Qwen/Qwen3.8-Flash-Next

Publisher

xpashkinView publisher statistics →

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

Similar models

xpashkin/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-6.8bpw — Downloads, Growth & Stats | OpenModelStats