GGUF models by cstr

462 GGUF models quantized by cstr on Hugging Face. Sizes run from 1M to 10.7B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
BA
bagel dpo 7b v0.5
Bagel · cstr
Params7.24B
Context32K
Smallest4.4 GB
GGUF
WA
wav2vec2 base german cv9
Wav · cstr
Params94M
Context—
Smallest0.1 GB
GGUF
MO
moonshine-tiny
Moonshine · cstr
Params27M
Context—
Smallest0.0 GB
GGUF
CL
clip vit base patch16
Clip · cstr
Params86M
Context—
Smallest0.3 GB
GGUF
CL
clip vit large patch14 336
Clip · cstr
Params304M
Context—
Smallest1.2 GB
GGUF
MO
moonshine-tiny
Moonshine · cstr
Params27M
Context—
Smallest0.0 GB
GGUF
WA
wav2vec2 xls r 1b german
Wav · cstr
Params963M
Context—
Smallest0.6 GB
GGUF
LL
llama3.1 8b spaetzle v59
Llama · cstr
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
llama3 8b spaetzle v39
Llama · cstr
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MO
moonshine-tiny
Moonshine · cstr
Params27M
Context—
Smallest0.0 GB
GGUF
NA
nanonets ocr2 1.5b crispembed
Nanonets · cstr
Params1.65B
Context—
Smallest1.4 GB
GGUF
AL
Spaetzle v60 7b Q4 0
Alphamonarch · cstr
Params7.24B
Context32K
Smallest4.1 GB
GGUF
LL
llama3.1 8b spaetzle v74
Llama · cstr
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
llama3 8b spaetzle v39 q4 0
Llama · cstr
Params8.03B
Context8K
Smallest4.7 GB
GGUF
LL
Llama3 DiscoLeo Instruct 8B 32k v0.1
Llama · cstr
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
WA
wav2vec2 large xlsr 53 german cv13
Wav · cstr
Params315M
Context—
Smallest0.2 GB
GGUF
WA
wav2vec2 xls r 1b tevr
Wav · cstr
Params963M
Context—
Smallest0.6 GB
GGUF
LL
llama3.1 8b spaetzle v90
Llama · cstr
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
OR
OrpoLlama 3 8B
Orpollama · cstr
Params8.03B
Context8K
Smallest4.9 GB
GGUF
OP
openvoice2 tcc
Openvoicev · cstr
Params33M
Context—
Smallest0.1 GB
GGUF
MA
madlad400 7b mt bt
Madlad · cstr
Params8.3B
Context—
Smallest0.0 GB
GGUF

Keep browsing