GGUF models: gpl-3.0 license

272 GGUF models listed under the gpl-3.0 license on Hugging Face. Always read the license text before commercial use. Sizes run from 1M to 72.3B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
SA
Sarvam Translate
Sarvam · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
QW
Qwen3.5 0.8B Dark Genius
Qwen · mradermacher
Params773M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
QW
Qwen2.5 14B Instruct Uncensored
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
BE
35b-beta-long
Beta · bartowski
Params35B
Context125K
Q4_K_M21.5 GB
Tool use
NE
Newton Bot 3
Newton · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
CodingTool use
QW
Qwen2.5 14B Instruct Uncensored
Qwen · yemiao2745
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
SA
salamandraTA 7b Instruct
Salamandrata · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 3B YiLin GGUF Q4_K_M
Qwen · likewendy
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
QW
Qwen2.5 14B Instruct Uncensored
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
DG
Dgpl Linux Assistant 0.8b
Dgpl · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
GU
guanaco 7b leh v2 i1
Guanaco · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
RE
RetroDFM R v0 8B
Retrodfm · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
causallm_8x7b-moe-test-not-mixtral
Mistral · TheBloke
Params38B
Context32K
Q4_K_M22.1 GB
GGUF
LL
Llama 2 7b Chat TruthX
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
Qwen3 VL 8B Maid
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
LU
XL LuaCopilot 1.7B FFT
Luacopilot · nwdxlgzs
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
SH
ShweYon V2.1 SFT
Shweyon · URajinda
Params120M
Context1K
Smallest0.1 GB
GGUF
QW
Models Orion Zhen Qwen2.5 7B Instruct Uncensored
Qwen · MaziyarPanahi
Params7.62B
Context32K
Smallest5.3 GB
GGUF
NE
Newton Bot 3 VLM Mini 4B
Newton · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningTool useVision
NE
Newton Bot 2A Standard_Merged
Newton · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
GP
Gpt2 Hertiage Foundation
Gpt · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
QW
Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
Qwen · featherless-ai-quants
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen3 30B A3B Thinking 2507 1M
Qwen · Orion-zhen
Params30.5B
Context1024K
Q4_K_M18.6 GB
ReasoningTool use
DE
DeepSeek V3 7B Drama Script Review
DeepSeek · mradermacher
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
BE
CausalLM 35b beta long
Beta · QuantFactory
Params35B
Context8K
Q4_K_M21.5 GB
Tool use
NE
Newton Bot 3
Newton · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
CodingTool use
GE
sarvam-translate
Gemma · Mungert
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
GE
apocalypse aid gemma4 e2b
Gemma · DestinyApocalypse
Params4.63B
Context128K
Smallest2.6 GB
ReasoningTool useVision
LL
Llama 3 Lunar 8B v0.2 i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 30B A3B Instruct 2507 1M
Qwen · Orion-zhen
Params30.5B
Context1024K
Q4_K_M18.6 GB
ReasoningTool use

Keep browsing