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
LL
LLaMAX3-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AC
ActionGemma 9B
Actiongemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
Tool use
QW
qwen 2 5 3b instruct using openai gsm8k data enhanced with deepseek v3
Qwen · eagle0504
Params3.09B
Context32K
Q4_K_M1.9 GB
ReasoningTool use
RL
RLAnything Coder 7B
Rlanything · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
HA
harrier 270m
Harrier · cstr
Params268M
Context32K
Smallest0.2 GB
Embedding
GL
GLM 4.7 Flash Heretic
GLM · mradermacher
Params29.9B
Context198K
Q4_K_M18.1 GB
ReasoningTool use
OC
OceanGPT O 7B
Oceangpt · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Tool useVision
QW
MiMo V2.6 Distill Qwen 9B ReasonMaxxer
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
PH
Borea Phi 3.5 Mini Instruct Common
Phi · mmnga
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
VO
Voice Realtime 1b 10
Voice · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
GE
Embedding Gemma 300m
Gemma · rizkysulaeman
Params303M
Context2K
Q4_K_M0.2 GB
Embedding
PA
MS3.2 PaintedFantasy v4.1 24B
Paintedfantasy · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingRoleplay
LL
doktor llama 3 cosmos 8b
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AL
AlphaMed 7B Base Rl
Alphamed · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
SM
NuExtract 1.5 Smol
SmolLM · QuantFactory
Params1.81B
Context8K
Q4_K_M1.1 GB
GGUF
OR
Ornith 1.5 9B OBLITERATED
Ornith · 0xSojalSec
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
QW
UnifiedReward Think Qwen35 9b
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
OR
Ornith 1.0 9B Heretic MTP
Ornith · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool use
DE
qwen 2 5 3b instruct using openai gsm8k data enhanced with deepseek v4
DeepSeek · eagle0504
Params3.09B
Context32K
Q4_K_M1.9 GB
ReasoningTool use
MI
MiniMaxAI_MiniMax M2
Minimax · lmstudio-community
Params229B
Context192K
Q4_K_M138.3 GB
ReasoningTool use
QW
AceCoder Qwen2.5 Coder 7B Ins V1.1
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
SU
Superthoughts Mini v1
Superthoughts · mradermacher
Params3.82B
Context128K
Q4_K_M2.3 GB
Reasoning
PH
Phi 4 Mini Instruct
Phi · professorf
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingTool use
MO
Mocha Coder 32B
Mocha · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
CodingTool use
GL
GLM 4 32B Base 0414
GLM · mradermacher
Params32.6B
Context32K
Q4_K_M19.7 GB
GGUF
GL
Zai org.GLM 4.7 Flash
GLM · DevQuasar
Params29.9B
Context198K
Q4_K_M18.1 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · matrixportalx
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
OR
Ornith 1.0 35B Heretic MTP
Ornith · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
MI
Heidrun Mistral 7B chat
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
QW
UnifiedReward Qwen 32b
Qwen · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
Vision

Keep browsing