How to use from
Ollama
ollama run hf.co/noctrex/AI21-Jamba-Mini-1.7-MXFP4_MOE-GGUF:MXFP4_MOE
Quick Links

This is a MXFP4_MOE quantization of the model AI21-Jamba-Mini-1.7

Model quantized with F16 GGUF's from: https://huggingface.co/DevQuasar/ai21labs.AI21-Jamba-Mini-1.7-GGUF

Original model: https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.7

Downloads last month
6
GGUF
Model size
52B params
Architecture
jamba
Hardware compatibility
Log In to add your hardware

4-bit

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

Model tree for noctrex/AI21-Jamba-Mini-1.7-MXFP4_MOE-GGUF

Quantized
(6)
this model