Downloads · 30 days
182
34% of all-time downloads
KAT-Coder-V2.5-Dev-MLX-8bit
majentik/KAT-Coder-V2.5-Dev-MLX-8bit
KAT-Coder-V2.5-Dev-MLX-8bit is a text generation model from majentik. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
MLX 8bit (affine, group size 64) quantized variant of Kwaipilot/KAT-Coder-V2.5-Dev for Apple silicon via mlx-lm.
All-time downloads
535
Public
Parameters
34.7B
36.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors36.8 GB · 100%
Parameter types
How the weights are stored.
U3234.7B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
KAT-Coder-V2.5-Dev-MLX-8bit
MLX 8bit (affine, group size 64) quantized variant of Kwaipilot/KAT-Coder-V2.5-Dev for Apple silicon via mlx-lm.
Provenance
- Source: Kwaipilot/KAT-Coder-V2.5-Dev @ revision
7be56fe773e72b6f5ca93c1ae45d828ddb893922(Apache-2.0). - Quantized with
mlx_lm.convert(mlx-lm 0.31.3): affine, 8-bit, group size 64. - Text-only pack: the upstream checkpoint is multimodal
(
Qwen3_5MoeForConditionalGeneration); mlx-lm'sqwen3_5_moeloader drops the vision tower (model.visual.*) by design, so this pack ships only the text MoE. Use the upstream repo if you need vision.
Smoke gate
Before upload this pack passed a deterministic coherence gate: greedy
64-token chat generation loaded through mlx_lm.load,
judged for emptiness, repetition loops, multi-script gibberish, and
special-token debris. Verdict: ok.
Usage
pip install mlx-lm
mlx_lm.generate --model majentik/KAT-Coder-V2.5-Dev-MLX-8bit --prompt "Write a binary search in Python"
Evaluation
| Benchmark | Score |
|---|---|
| arc_easy_acc | 0.6700 |
| hellaswag_acc | 0.5300 |
Available tiers
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5_moe
- License
- apache-2.0
- Created
- Aug 9, 2026
- Updated
- Aug 17, 2026