GGUF models by lm-kit

109 GGUF models quantized by lm-kit on Hugging Face. Sizes run from 33M to 70.6B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
qwen 2 7b instruct
Qwen · lm-kit
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
SM
SmolLM3 3B
SmolLM · lm-kit
Params3.08B
Context64K
Q4_K_M1.9 GB
ReasoningTool use
FA
Falcon H1R 7B
Falcon · lm-kit
Params7.59B
Context256K
Q4_K_M4.6 GB
ReasoningTool use
DE
deepseek coder 1.6 7b
DeepSeek · lm-kit
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
NE
nemotron 3 nano 4b
Nemotron · lm-kit
Params3.97B
Context1024K
Q4_K_M2.8 GB
ReasoningTool use
QW
qwen3.5 9b lmk
Qwen · lm-kit
Params9.2B
Context256K
Smallest18.4 GB
ReasoningTool useVision
LL
llama 3.3 70b instruct
Llama · lm-kit
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
MU
Muse Glimmer 30b
Muse · lm-kit
Params27.9B
Context128K
Smallest55.7 GB
ReasoningTool useVision
GE
gemma 3 4b instruct lmk
Gemma · lm-kit
Params3.88B
Context128K
Smallest7.8 GB
Vision
QW
Qwen3 Embedding 8B
Qwen · lm-kit
Params7.57B
Context40K
Q4_K_M4.7 GB
EmbeddingTool use
GP
gpt oss 20b
gpt-oss · lm-kit
Params20.9B
Context128K
Smallest12.1 GB
Tool use
GE
gemma 4 31b instruct lmk
Gemma · lm-kit
Params30.7B
Context256K
Smallest61.4 GB
ReasoningTool useVision
GR
granite 3.1 2.5b instruct
Granite · lm-kit
Params2.53B
Context128K
Q4_K_M1.5 GB
Tool use
GR
Granite 3.3 2b Instruct
Granite · lm-kit
Params2.53B
Context128K
Q4_K_M1.5 GB
ReasoningTool use
QW
qwq 32b
Qwen · lm-kit
Params32.8B
Context40K
Q4_K_M19.9 GB
ReasoningTool use
MI
mistral 0.3 7b
Mistral · lm-kit
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
GE
gemma 3 12b instruct lmk
Gemma · lm-kit
Params11.8B
Context128K
Smallest23.5 GB
Vision
GR
Granite 4.0 H Tiny
Granite · lm-kit
Params6.94B
Context1024K
Q4_K_M4.2 GB
Tool use
QW
qwen3 vl 4b instruct lmk
Qwen · lm-kit
Params4.02B
Context256K
Smallest8.1 GB
Tool useVision
KI
lm kit sentiment analysis 2.0 1b
Kit · lm-kit
Params1.24B
Context128K
Smallest0.8 GB
Tool use
GE
gemma 2 2b
Gemma · lm-kit
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
QW
qwen2 vl 2b instruct lmk
Qwen · lm-kit
Params1.54B
Context32K
Smallest3.1 GB
Vision
GR
Granite 3.3 8b Instruct
Granite · lm-kit
Params8.17B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
QW
qwen3.5 0.8b lmk
Qwen · lm-kit
Params773M
Context256K
Smallest1.6 GB
ReasoningTool useVision
GE
gemma 4 26b a4b instruct lmk
Gemma · lm-kit
Params25.2B
Context256K
Smallest50.5 GB
ReasoningTool useVision
PA
paddle ocr vl 1.5 lmk
Paddle · lm-kit
Params467M
Context128K
Smallest0.9 GB
Vision
MI
Magistral Small 2506
Mistral · lm-kit
Params23.6B
Context40K
Q4_K_M14.3 GB
ReasoningTool use
NE
NVIDIA Nemotron 3 Nano 30B A3B BF16
Nemotron · lm-kit
Params31.6B
Context1024K
Q4_K_M24.5 GB
ReasoningTool use
LI
lightonocr 2 1b bbox soup lmk
Lightonocr · lm-kit
Params596M
Context16K
Smallest1.2 GB
Vision
QW
qwen3.5 27b lmk
Qwen · lm-kit
Params27.3B
Context256K
Smallest54.7 GB
ReasoningTool useVision

Keep browsing