Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
eaddario
/
Qwen3-30B-A3B-pruned-GGUF
like
4
Text Generation
GGUF
eaddario/imatrix-calibration
English
quant
pruned
experimental
imatrix
conversational
arxiv:
2406.17415
arxiv:
2403.03853
License:
apache-2.0
Model card
Files
Files and versions
Community
Deploy
Use this model
c02e889
Qwen3-30B-A3B-pruned-GGUF
Ctrl+K
Ctrl+K
1 contributor
History:
10 commits
eaddario
Layer-wise & pruned quantization Q6_K
c02e889
verified
about 1 month ago
imatrix
Generate imatrices
about 1 month ago
logits
Generate base model logits
about 1 month ago
.gitattributes
Safe
1.6 kB
Update .gitattributes
about 1 month ago
.gitignore
Safe
6.78 kB
Add .gitignore
about 1 month ago
Qwen3-30B-A3B-F16-00001-of-00003.gguf
Safe
24.7 GB
LFS
Convert safetensor to GGUF @ F16
about 1 month ago
Qwen3-30B-A3B-F16-00002-of-00003.gguf
Safe
24.9 GB
LFS
Convert safetensor to GGUF @ F16
about 1 month ago
Qwen3-30B-A3B-F16-00003-of-00003.gguf
Safe
11.4 GB
LFS
Convert safetensor to GGUF @ F16
about 1 month ago
Qwen3-30B-A3B-pruned-Q6_K.gguf
Safe
24.2 GB
LFS
Layer-wise & pruned quantization Q6_K
about 1 month ago
Qwen3-30B-A3B-pruned-Q8_0.gguf
Safe
28.6 GB
LFS
Layer-wise & pruned quantization Q8_0
about 1 month ago
README.md
Safe
31 Bytes
initial commit
about 1 month ago
