#Experimental #Testing

Output format:

<think>
...
</think>
Response here.

GGUF

Model size

12.2B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Lewdiculous/Irix-12B-Reasoner-v.0.2-GGUF-IQ-Imatrix

Base model

Finetuned

Quantized

(3)

this model