Downloads · 30 days
229
33% of all-time downloads
KAT-Coder-V2.5-Dev-oQ4e-fp16
ZQ-Dev/KAT-Coder-V2.5-Dev-oQ4e-fp16
KAT-Coder-V2.5-Dev-oQ4e-fp16 is a text generation model from ZQ-Dev. 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.
A 4-bit enhanced oQ quantization of Kwaipilot/KAT-Coder-V2.5-Dev for Apple Silicon and MLX-compatible runtimes.
All-time downloads
686
Public
Parameters
34.7B
20.4 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors20.4 GB · 100%
Parameter types
How the weights are stored.
U3234.6B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
KAT-Coder-V2.5-Dev-oQ4e
A 4-bit enhanced oQ quantization of Kwaipilot/KAT-Coder-V2.5-Dev for Apple Silicon and MLX-compatible runtimes.
Quantization details
The full calibration summary is available in
oq_imatrix_report.json.
Note: This quant was created using float16 non-quant weights. Per oMLX, float16 gives ~20% faster prefill on M1/M2 Apple Silicon (native fp16). bfloat16 is safer on M3+ and for numerical stability. For the standard oQe with bfloat16, see this repo.
License
Apache 2.0, inherited from the base model.
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5_moe
- License
- apache-2.0
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026