SicariusSicariiStuff
/

Impish_Nemo_12B_GGUF_HA

Model card Files Files and versions Community

What is this?

These are dynamic gguf quants, they take slightly more VRAM, but the attention layers are of a much higher quality.

Downloads last month: 3,839

GGUF

Model size

12.2B params

Architecture

llama

Hardware compatibility

Log In to view the estimation

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for SicariusSicariiStuff/Impish_Nemo_12B_GGUF_HA

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Finetuned

SicariusSicariiStuff/Impish_Nemo_12B

Quantized

(37)

this model

Dataset used to train SicariusSicariiStuff/Impish_Nemo_12B_GGUF_HA