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
ST
stable-code-instruct-3b
Stable · lmstudio-community
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
DE
deepseek-coder-1.3B-kexer
DeepSeek · lmstudio-community
Params1.35B
Context16K
Q4_K_M0.9 GB
Coding
PH
Phi 3.1 mini 4k instruct
Phi · lmstudio-community
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
MI
mistralai_Ministral 3 3B Reasoning 2512
Mistral · lmstudio-community
Params3.43B
Context256K
Q4_K_M2.1 GB
ReasoningVision
MI
MiniCPM V 2 6
MiniCPM · lmstudio-community
Params7.6B
Context32K
Q4_K_M4.7 GB
CodingVision
MI
mistralai_Devstral Small 2507
Mistral · lmstudio-community
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding
QW
Qwen3 Coder 480B A35B Instruct
Qwen · lmstudio-community
Params480B
Context256K
Q4_K_M290.8 GB
Coding
MI
Mistral Small 24B Instruct 2501
Mistral · lmstudio-community
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
OL
allenai_Olmo 3 32B Think
OLMo · lmstudio-community
Params32.2B
Context64K
Q4_K_M19.5 GB
Reasoning
GP
gpt oss safeguard 20b
gpt-oss · lmstudio-community
Params20.9B
Context128K
Smallest12.1 GB
GGUF
MI
Mistral Small 3.1 24B Instruct 2503
Mistral · lmstudio-community
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
GE
Gemma 3 4b
Gemma · lmstudio-community
Params3.88B
Context128K
Smallest2.4 GB
Vision
TA
UI TARS 2B SFT
Tars · lmstudio-community
Params1.78B
Context32K
Q4_K_M1.1 GB
Vision
LL
Llama-3-Groq-70B-Tool-Use
Llama · lmstudio-community
Params70.6B
Context8K
Q4_K_M42.5 GB
Tool use
QW
Qwen3 235B A22B Instruct 2507
Qwen · lmstudio-community
Params235B
Context256K
Q4_K_M142.6 GB
GGUF
LL
Llama 4 Scout 17B 16E Instruct
Llama · lmstudio-community
Params108B
Context10240K
Q4_K_M67.5 GB
Vision
YI
Yi-1.5-9B-Chat
Yi · lmstudio-community
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
GE
gemma 3n E2B it text
Gemma · lmstudio-community
Params4.46B
Context32K
Q4_K_M2.8 GB
GGUF
EM
EmbeddingGemma 300m
Embeddinggemma · lmstudio-community
Params303M
Context2K
Smallest0.2 GB
Embedding
GE
Gemma 3 12b
Gemma · lmstudio-community
Params11.8B
Context128K
Smallest6.9 GB
Vision
GR
Granite 3.1 8b Instruct
Granite · lmstudio-community
Params8.17B
Context128K
Q4_K_M4.9 GB
GGUF
ST
starcoder2-15b-instruct-v0.1
StarCoder · lmstudio-community
Params16B
Context16K
Q4_K_M9.9 GB
Coding
MI
MiniMaxAI_MiniMax M2.5
Minimax · lmstudio-community
Params230B
Context192K
Q4_K_M138.3 GB
GGUF
NE
NVIDIA Nemotron 3.5 Bolt E4B
Nemotron · lmstudio-community
Params7.52B
Context128K
Q4_K_M6.2 GB
ReasoningTool use
GR
Ibm Granite_Granite 4.2 8b
Granite · lmstudio-community
Params8.79B
Context128K
Q4_K_M5.3 GB
GGUF
QW
Qwen2 VL 7B Instruct
Qwen · lmstudio-community
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
IN
InternVL3_5 2B
Internvl · lmstudio-community
Params2.03B
Context40K
Q4_K_M1.3 GB
Vision
LL
Cogito v1 Preview Llama 3B
Llama · lmstudio-community
Params3.61B
Context128K
Q4_K_M2.2 GB
ReasoningTool use
WA
wavecoder ultra 6.7b
Wavecoder · lmstudio-community
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Qwen2.5 72B Instruct
Qwen · lmstudio-community
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF

Keep browsing