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
Qwen3.8 27b
Qwen · lm-kit
Params27.3B
Context256K
Smallest54.7 GB
ReasoningTool useVision
QW
qwen3.6 27b lmk
Qwen · lm-kit
Params27.3B
Context256K
Smallest54.7 GB
ReasoningTool useVision
QW
qwen3 vl 30b instruct lmk
Qwen · lm-kit
Params30.5B
Context256K
Smallest61.1 GB
Tool useVision
QW
qwen3.5 35b a3b lmk
Qwen · lm-kit
Params35.5B
Context256K
Smallest71.1 GB
ReasoningTool useVision
LL
llama 3 8b instruct
Llama · lm-kit
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
qwen3 vl 2b instruct lmk
Qwen · lm-kit
Params1.72B
Context256K
Smallest3.4 GB
Tool useVision
QW
qwen3.5 2b lmk
Qwen · lm-kit
Params1.94B
Context256K
Smallest3.9 GB
ReasoningTool useVision
QW
qwen3.6 35b a3b lmk
Qwen · lm-kit
Params35.5B
Context256K
Smallest71.1 GB
ReasoningTool useVision
KI
LM Kit.Sarcasm Detection TinyLlama 1.1B 1T OpenOrca en q4
Kit · lm-kit
Params1.1B
Context2K
Smallest0.7 GB
GGUF
GL
glm 4.6v flash lmk
GLM · lm-kit
Params9.4B
Context128K
Smallest18.8 GB
ReasoningTool useVision
QW
qwen2.5 vl 3b instruct lmk
Qwen · lm-kit
Params3.09B
Context125K
Smallest6.2 GB
Vision
MI
magistral-small-2509
Mistral · lm-kit
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
KI
LM-Kit.Sentiment_Analysis-TinyLlama-1.1B-1T-OpenOrca-en-q4
Kit · lm-kit
Params1.1B
Context2K
Smallest0.7 GB
GGUF
QW
qwen3 vl 8b instruct lmk
Qwen · lm-kit
Params8.19B
Context256K
Smallest16.4 GB
Tool useVision
QW
qwen2 vl 8.3b instruct lmk
Qwen · lm-kit
Params7.62B
Context32K
Smallest15.2 GB
Vision
MI
mistral small 3.2 2506 24b instruct
Mistral · lm-kit
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QW
qwen2.5 vl 7b instruct lmk
Qwen · lm-kit
Params7.62B
Context125K
Smallest15.2 GB
Vision
LI
lightonocr 2 1b lmk
Lightonocr · lm-kit
Params596M
Context16K
Smallest1.2 GB
GGUF
LI
lightonocr 1b 1025 lmk
Lightonocr · lm-kit
Params752M
Context8K
Smallest1.5 GB
GGUF

Keep browsing