GGUF models by abarelka

35 GGUF models quantized by abarelka on Hugging Face. Sizes run from 8.03B to 8.03B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
BI
L318B 16bitGGUF ST UST B7
Bitgguf · abarelka
Params8.03B
Context128K
Smallest16.1 GB
Tool use
BI
L318B 16bitGGUF ST7 all OCMsT
Bitgguf · abarelka
Params8.03B
Context128K
Smallest16.1 GB
Tool use
US
ST_UST_3.1_8B_16gguf_all_OCMs NOAFMS
Ust · abarelka
Params8.03B
Context128K
Smallest16.1 GB
Tool use
BI
L318B 16bitGGUF Unstru UST ST
Bitgguf · abarelka
Params8.03B
Context128K
Smallest16.1 GB
Tool use
LL
L318B Q8 0 ST7OCM UST1102
Llama · abarelka
Params8.03B
Context128K
Smallest8.5 GB
Tool use

Keep browsing