Hugging Face's logo

Nan-Do
/
FusionNet_7Bx2_MoE_14B-GGUF

GGUF
mixtral
Mixture of Experts
quantization
Model card Files Community
FusionNet_7Bx2_MoE_14B-GGUF / README.md
Nan-Do's picture
Nan-Do
Fixed the model_creator meta data field
8b4a2ed verified
preview code
|
raw history blame contribute delete
No virus
2.45 kB
metadata
base_model: TomGrc/FusionNet_7Bx2_MoE_14B
inference: true
license: mit
model-index:
  - name: FusionNet_7Bx2_MoE_14B
    results: []
model_creator: TomGrc
model_name: FusionNet_7Bx2_MoE_14B
model_type: mixtral
quantized_by: Nan-Do
tags:
  - mixtral
  - Mixture of Experts
  - quantization

FusionNet_7Bx2_MoE_14B

Description

This repo contains GGUF format model files for FusionNet_7Bx2_MoE_14B.

Provided files

Name Quantisation method Bits Size
FusionNet_7Bx2_MoE_14B-Q3_K_S.gguf Q3_KS 3 5.59 GB
FusionNet_7Bx2_MoE_14B-Q3_K.gguf Q3_K 3 6.21 GB
FusionNet_7Bx2_MoE_14B-Q4_0.gguf Q4_0 4 7.28 GB
FusionNet_7Bx2_MoE_14B-Q4_K_S.gguf Q4_K_S 4 7.34 GB
FusionNet_7Bx2_MoE_14B-Q4_K.gguf Q4_K 4 7.78 GB
FusionNet_7Bx2_MoE_14B-Q4_1.gguf Q4_1 4 8.08 GB
FusionNet_7Bx2_MoE_14B-Q5_K_S.gguf Q5_KS 5 8.87 GB
FusionNet_7Bx2_MoE_14B-Q5_K.gguf Q5_K 5 9.13 GB
FusionNet_7Bx2_MoE_14B-Q6_K.gguf Q6_K 6 10.6 GB
FusionNet_7Bx2_MoE_14B-Q8_0.gguf Q8_0 8 13.7 GB