Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ubergarm
/
GLM-4.5-Air-GGUF
like
27
Text Generation
GGUF
imatrix
conversational
ik_llama.cpp
License:
mit
Model card
Files
Files and versions
Community
6
Deploy
Use this model
main
GLM-4.5-Air-GGUF
/
README.md
Commit History
fixup readme
e0bb40e
ubergarm
commited on
29 days ago
Release IQ3_KS with perplexity info
fa40640
ubergarm
commited on
29 days ago
Support added into ik_llama.cpp main branch now yay!
482e5b8
ubergarm
commited on
about 1 month ago
Add IQ1_KT (with iq4_nl ffn_down_exps lmao)
14e974e
ubergarm
commited on
about 1 month ago
update readme with IQ4_K and IQ5_KS
c738943
ubergarm
commited on
about 1 month ago
Uploading IQ4_K and IQ5_KSS
726f6c5
ubergarm
commited on
about 1 month ago
fixup IQ4_KSS recipe
d968e06
ubergarm
commited on
about 1 month ago
add recipes and perplexity graph
1ae325a
ubergarm
commited on
about 1 month ago
fixup readme
4ab18fb
ubergarm
commited on
Aug 6
Upload IQ2_KL and add perplexity values
6eb7b85
ubergarm
commited on
Aug 6
Add IQ5_K 6BPW with similar PPL as Q8_0
d047f0a
ubergarm
commited on
Aug 6
Add --chat-template chatglm4 again for /nothink
607ffea
ubergarm
commited on
Aug 5
Add BF16 Perplexity
e3c5f49
ubergarm
commited on
Aug 5
add two perplexity numbers
50de40a
ubergarm
commited on
Aug 5
Updating imatrix and IQ4_KSS
874fab4
ubergarm
commited on
Aug 5
May need --override-kv tokenizer.ggml.eot_token_id=int:151336
f2eb604
ubergarm
commited on
Aug 3
Update WARNING EXPERIMENTAL quant instructions
6aa5bab
ubergarm
commited on
Aug 2
WARNING EXPERIMENTAL IQ4_KSS
30a0b69
ubergarm
commited on
Aug 2
add BF16 and Q8_0 size info
bc32e07
ubergarm
commited on
Aug 2
initial commit
6a83919
verified
ubergarm
commited on
Aug 2
ubergarm
commited on
