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 Embedding 4B
Qwen · lm-kit
Params4.02B
Context40K
Q4_K_M2.5 GB
EmbeddingTool use
BG
bge 1.5
BGE · lm-kit
Params33M
Context512
Smallest0.1 GB
Embedding
PA
paddle ocr vl 1.6 lmk
Paddle · lm-kit
Params467M
Context128K
Smallest0.9 GB
Vision
GE
gemma 2 9b
Gemma · lm-kit
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
FA
falcon 3 3.2b instruct
Falcon · lm-kit
Params3.23B
Context32K
Q4_K_M2.0 GB
GGUF
FA
falcon 3 7.6b instruct
Falcon · lm-kit
Params7.46B
Context32K
Q4_K_M4.6 GB
Tool use
GE
gemma 3 27b instruct
Gemma · lm-kit
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
EM
embeddinggemma 2 lmk
Embeddinggemma · lm-kit
Params271M
Context256K
Smallest0.2 GB
EmbeddingVision
QW
Qwen3 Coder 30B A3B Instruct
Qwen · lm-kit
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
TI
tinyllama 1.0 1.1b chat
Tinyllama · lm-kit
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
MI
mistral small 2501 24b instruct
Mistral · lm-kit
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
MI
mistral 0.3 7b instruct
Mistral · lm-kit
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
LI
LightOnOCR 3 0.8B
Lightonocr · lm-kit
Params752M
Context256K
Smallest1.5 GB
ReasoningTool useVision
QW
qwen 2.5 0.5b instruct
Qwen · lm-kit
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
LL
tiny llama 1.1 1.1b
Llama · lm-kit
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
LI
LightOnOCR 3 4B
Lightonocr · lm-kit
Params4.21B
Context256K
Smallest8.4 GB
ReasoningTool useVision
GE
gemma 4 e4b instruct lmk
Gemma · lm-kit
Params7.52B
Context128K
Smallest15.1 GB
ReasoningTool useVision
LI
LightOnOCR 3 1B
Lightonocr · lm-kit
Params596M
Context16K
Smallest1.2 GB
Vision
TR
translategemma 3 4b instruct lmk
Translategemma · lm-kit
Params3.88B
Context128K
Smallest7.8 GB
Vision
FA
falcon 3 10.3b instruct
Falcon · lm-kit
Params10.3B
Context32K
Q4_K_M6.3 GB
GGUF
DE
deepseek coder 2 lite 15.7b
DeepSeek · lm-kit
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
TR
translategemma 3 12b instruct lmk
Translategemma · lm-kit
Params11.8B
Context128K
Smallest23.5 GB
Vision
MI
mistral 0.1 openorca 7b
Mistral · lm-kit
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
deepseek r1 distill llama 8b
DeepSeek · lm-kit
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
MI
mistral small 3.1 2503 24b instruct
Mistral · lm-kit
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
LL
llama 3.1 8b instruct
Llama · lm-kit
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
GE
gemma 4 12b instruct lmk
Gemma · lm-kit
Params11.9B
Context256K
Smallest23.8 GB
ReasoningTool useVision
QW
qwen3.5 4b lmk
Qwen · lm-kit
Params4.33B
Context256K
Smallest8.7 GB
ReasoningTool useVision
GR
Granite 4.0 H Micro
Granite · lm-kit
Params3.19B
Context1024K
Q4_K_M1.9 GB
Tool use
GR
granite 3.1 8b instruct
Granite · lm-kit
Params8.17B
Context128K
Q4_K_M4.9 GB
Tool use

Keep browsing