GGUF models: mit license

17492 GGUF models listed under the mit license on Hugging Face. Always read the license text before commercial use. Sizes run from 1M to 5632B parameters. The longest trained context is 97656K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
K intelligence.Midm 2.0 Base Instruct
Midm · DevQuasar
Params11.5B
Context32K
Q4_K_M7.0 GB
Tool use
QW
MM RAIT Qwen2.5 VL
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
GL
GLM 4.5 Air
GLM · auRose94
Params110B
Context128K
Smallest63.5 GB
GGUF
QO
QoQ Med3 VL 8B MIMIC
Qoq · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
DO
Dots.Ocr
Dots · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
Coding
BG
baai bge m3 568m
BGE · cPilotGod
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
DE
Deimos A1
Deimos · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
LL
Cakrawala 8B i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · matrixportalx
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
QW
Majority Voting Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
JO
JOSIE 2 4B Preview
Josie · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningTool useVision
LO
M3.2 24B Loki V1.2
Loki · CrucibleLab-TG
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
DE
DeepSeek R1 Distill Qwen 14B Heretic
DeepSeek · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
NE
NeuralJaskier 7b dpo i1
Neuraljaskier · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OR
Ornith 1.5 397B uncensored
Ornith · Lethevimlet
Params396B
Context256K
Smallest228.2 GB
Vision
DI
DianJin R1 32B
Dianjin · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
LI
Ling 3.0 flash VL MTP ROCmFP4
Ling · kingjones777
Params124B
Context128K
Smallest66.5 GB
Vision
SO
SocialR1 4B
Socialr · mradermacher
Params4.41B
Context40K
Q4_K_M2.7 GB
ReasoningTool use
IN
Inexpertus 1.1 8B LINEAR i1
Inexpertus · BasedAGI
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
WH
whisper large v3
Whisper · oxide-lab
Params1.61B
Context—
Smallest0.5 GB
GGUF
MI
Mithra 2B
Mithra · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
NE
Next2 0.8b
Next · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
SE
SenseNova MARS 8B
Sensenova · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
SE
Sentiment Analysis 7B
Sentiment · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
DeepSeek V4.1 Flash 1017 Abliteration LoRA
DeepSeek · BoldingBuilds
Params115M
Context—
Smallest0.5 GB
GGUF
DE
deepseek r1 distill qwen 1 5b q4 k m llamacpp vivo x300
DeepSeek · Arm
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
KI
Kimi Linear 48B A3B Instruct
Kimi · DhruvalLabs
Params49.1B
Context1024K
Q4_K_M29.7 GB
CodingTool use
AE
Aeona i1
Aeona · mradermacher
Params355M
Context1K
Q4_K_M0.2 GB
GGUF
BE
Beck 8B
Beck · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
UnifiedReward Think Qwen3Vl 4b
Qwen · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use

Keep browsing