This is a MXFP4_MOE quantization of the model LLaDA-MoE-7B-A1B-Instruct-TD: A specialized instruction-tuned model, further optimized for accelerated inference using Trajectory Distillation.

Also created a quant with an imatrix from mradermacher.

Original model: https://huggingface.co/inclusionAI/LLaDA-MoE-7B-A1B-Instruct-TD

Downloads last month
492
GGUF
Model size
7B params
Architecture
llada-moe
Hardware compatibility
Log In to view the estimation

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for noctrex/LLaDA-MoE-7B-A1B-Instruct-TD-MXFP4_MOE-GGUF

Quantized
(3)
this model