Qwen3.8-27B-mlx-uniform-4bit-mtp-drafter
caslca/Qwen3.8-27B-mlx-uniform-4bit-mtp-drafter
425M parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since September 28, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 715
- Total downloadsCumulative all-time download counter reported by the source platform.
- 715
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +56(increase)
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 0
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- #36,989
- 210(down 210 places)this week
- Parameters
- 425M
- Last source update
- Sep 14, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 17.3
- Qwen3.8-27B-mlx-uniform-4bit-mtp-drafter gained 56 downloads during the last seven tracked days.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Qwen3.8-27B-mlx-uniform-4bit-mtp-drafter is an AI model published by caslca. OpenModelStats has tracked the model since Sep 28, 2026, most recently observing it Sep 15, 2026.
- Published
- Aug 27, 2026
- Last updated
- Sep 14, 2026
- Library
- mlx
- License
- apache-2.0
- Task
- —
- Parameters
- 424,699,392
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 8
mlxsafetensorsqwen3_5_mtpspeculative-decodingmtpbase_model:caslca/Qwen3.8-27B-mlx-uniform-4bitbase_model:quantized:caslca/Qwen3.8-27B-mlx-uniform-4bitlicense:apache-2.04-bitregion:us
Publisher
caslcaView publisher statistics →Derived from caslca/Qwen3.8-27B-mlx-uniform-4bit (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Qwen3.8-27B-MTP-4bitmlx-community | 20.8K |
| Qwen3.8-27B-MTP-8bitmlx-community | 4,418 |
| Qwen3.8-27B-MTP-bf16mlx-community | 1,969 |
| Qwen3.8-27B-Fable-Distill-OptiQ-4.5bpw-mixed-mtp-draftercaslca | 1,853 |
| Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-DrafterVisualInference | 1,818 |
| Qwen3.8-27B-AEON-Ultimate-MLX-MTP-DrafterVisualInference | 1,681 |