GGUF models by lmstudio-community

432 GGUF models quantized by lmstudio-community on Hugging Face. Sizes run from 30M to 671B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
BY
ByteCraft
Bytecraft · lmstudio-community
Params8.39B
Context32K
Q4_K_M5.2 GB
Tool use
ER
ERNIE 4.5 300B A47B PT
Ernie · lmstudio-community
Params299B
Context128K
Q4_K_M181.8 GB
GGUF
SK
Skywork OR1 7B
Skywork · lmstudio-community
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
EX
EXAONE 3.5 32B Instruct
Exaone · lmstudio-community
Params32B
Context32K
Q4_K_M19.3 GB
GGUF
IN
OREAL 32B
InternLM · lmstudio-community
Params32.8B
Context128K
Q4_K_M19.9 GB
Tool use
RE
Reka Flash 3.1
Reka · lmstudio-community
Params20.9B
Context96K
Q4_K_M13.6 GB
GGUF
XL
xLAM 7b R
Xlam · lmstudio-community
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
GL
Zai org_GLM 4.7
GLM · lmstudio-community
Params358B
Context198K
Q4_K_M216.2 GB
ReasoningTool use
IN
OREAL 7B
InternLM · lmstudio-community
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
SK
Skywork SWE 32B
Skywork · lmstudio-community
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
SK
Skywork OR1 32B
Skywork · lmstudio-community
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
MA
MAI DS R1
Mai · lmstudio-community
Params671B
Context160K
Q4_K_M404.5 GB
ReasoningTool use

Keep browsing