nace-ai drex-v1.5 (MLX 8-bit)
8-bit MLX conversion of nace-ai/drex-v1.5 for Apple Silicon (mlx_lm).
Origin and license
- Original weights: https://huggingface.co/nace-ai/drex-v1.5
- License:
other(NACE AI OPEN RAIL-M LICENSE (MODIFIED)) — carried over from the upstream weights; if anything conflicts, the upstream repository's LICENSE prevails. - Conversion: 8-bit quantization for MLX only; no retraining, no architecture changes.
Local LICENSE = OpenRAIL-M (modified), uploaded together with the weights
Usage
from mlx_lm import load, generate
model, tokenizer = load("sergolsub/mlx-drex-v1.5-8bit")
print(generate(model, tokenizer, prompt="...", max_tokens=256))
Files
*.safetensors— 8-bit weights (MLX layout)config.json,tokenizer*,chat_template.jinja— standard transformers/MLX set*_mlx.py/decision_config.json/joint_config.json— decision/joint-head inference glue (present when the model has a decision mode)
- Downloads last month
- -
Model size
9B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for sergolsub/mlx-drex-v1.5-8bit
Base model
Qwen/Qwen3.5-9B-Base Finetuned
Qwen/Qwen3.5-9B Finetuned
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B Finetuned
nace-ai/drex-v1.5