Model imatrix quants as requested at #36 for Sao10K/Fimbulvetr-11B-v2.
Prompt Format: Alpaca or Vicuna.

An absolute classic and highly popular roleplay model, now with newer quants as requested directly.

Imatrix data was generated from the FP16-GGUF and conversions as well since the original model weights are already FP16.
Using the latest version of llama.cpp at the time - b2774.

image/webp

Downloads last month
2,419
GGUF
Model size
10.7B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Inference API (serverless) has been turned off for this model.

Model tree for Lewdiculous/Fimbulvetr-11B-v2-GGUF-IQ-Imatrix

Quantized
(11)
this model