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
LL
Llama 3.1 8B UltraLong 2M Instruct
Llama · lmstudio-community
Params8.04B
Context2096K
Q4_K_M4.9 GB
Tool use
OL
allenai_Olmo 3.1 32B Instruct
OLMo · lmstudio-community
Params32.2B
Context64K
Q4_K_M19.5 GB
Tool use
OP
Openhands Lm 7b v0.1
Openhands · lmstudio-community
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
AC
AceInstruct 1.5B
Aceinstruct · lmstudio-community
Params1.78B
Context128K
Q4_K_M1.1 GB
Coding
QW
QVQ 72B Preview
Qwen · lmstudio-community
Params72.7B
Context125K
Q4_K_M47.4 GB
Vision
IN
INTELLECT 1 Instruct
Intellect · lmstudio-community
Params10.2B
Context8K
Q4_K_M6.2 GB
Coding
DE
DeepCoder 14B Preview
Deepcoder · lmstudio-community
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingReasoningTool use
EX
EXAONE Deep 32B
Exaone · lmstudio-community
Params32B
Context32K
Q4_K_M19.3 GB
GGUF
OL
OlympicCoder 32B
Olympiccoder · lmstudio-community
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingReasoningTool use
DE
DeepSWE Preview
Deepswe · lmstudio-community
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
NE
Apriel Nemotron 15b Thinker
Nemotron · lmstudio-community
Params15B
Context64K
Q4_K_M9.1 GB
ReasoningTool use
NE
AceReason Nemotron 1.1 7B
Nemotron · lmstudio-community
Params7.62B
Context128K
Q4_K_M4.7 GB
CodingReasoningTool use
EX
LGAI EXAONE_EXAONE 4.0 1.2B
Exaone · lmstudio-community
Params1.28B
Context64K
Q4_K_M0.8 GB
ReasoningTool use
OP
OpenThinker2 7B
Openthinker · lmstudio-community
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
MI
Hyperion 3.0 Mistral 7B DPO
Mistral · lmstudio-community
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SK
Skywork OR1 7B Preview
Skywork · lmstudio-community
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
GR
Granite 3.0 8b Instruct
Granite · lmstudio-community
Params8.17B
Context4K
Q4_K_M4.9 GB
Tool use
MI
MindLink 72B 0801
Mindlink · lmstudio-community
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
LL
r1 1776 distill llama 70b
Llama · lmstudio-community
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
ZR
ZR1 1.5B
lmstudio-community
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingTool use
GR
granite embedding 125m english
Granite · lmstudio-community
Params124M
Context512
Q4_K_M0.1 GB
Embedding
OP
openchat-3.6-8b-20240522
Openchat · lmstudio-community
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
XL
xLAM 8x7b R
Xlam · lmstudio-community
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
OP
OpenThinker2 32B
Openthinker · lmstudio-community
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
OP
OpenThinker3 7B
Openthinker · lmstudio-community
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
KE
Kevin 32B
Kevin · lmstudio-community
Params32.8B
Context40K
Q4_K_M19.9 GB
ReasoningTool use
LL
Llama 3.1 Tulu 3.1 8B
Llama · lmstudio-community
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
OL
allenai_Olmo 3 1125 32B
OLMo · lmstudio-community
Params32.2B
Context64K
Q4_K_M19.5 GB
GGUF
DE
DeepCoder 1.5B Preview
Deepcoder · lmstudio-community
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingTool use
DH
Dhanishtha 2.0 Preview
Dhanishtha · lmstudio-community
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use

Keep browsing