Q4_K_L GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 1891 models have a Q4_K_L file. Sizes run from 30M to 1030B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Meta Llama 3.1 8B Instruct
Llama · balajiduraisamy
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LF
LFM3 VL 2B
Lfm · bartowski
Params1.73B
Context125K
Q4_K_M1.1 GB
CodingReasoningTool use
HE
Hemmingway 1.5
Hemmingway · npario
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningTool use

Other quants

Keep browsing