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
KO
KoGemma dpo 7b v1
Kogemma · mradermacher
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
SA
sarvam translate 1.58bit
Sarvam · Mugunth123
Params3.88B
Context128K
Smallest1.2 GB
GGUF
SA
sarvam translate 2bit
Sarvam · Mugunth123
Params3.88B
Context128K
Smallest1.5 GB
GGUF
QW
Meissa Qwen2.5 7B Instruct
Qwen · Orion-zhen
Params7.62B
Context32K
Smallest5.4 GB
Roleplay
PH
Orion Zhen.Phi 4 Abliterated
Phi · DevQuasar-6
Params14.7B
Context16K
Q4_K_M9.1 GB
GGUF
GE
Gemma 2 2b Chinese It
Gemma · mradermacher
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
LL
MIXdevAI Llama
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
CodingReasoningTool use
QW
Qwen1.5 7B Translator
Qwen · mradermacher
Params7.72B
Context32K
Q4_K_M5.5 GB
GGUF
LL
Tiny_Llama_Storyteller
Llama · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
SA
Safelm 1.7b Heretic
Safelm · mradermacher
Params1.81B
Context8K
Q4_K_M1.1 GB
GGUF
LU
XL LuaCopilot 0.6B FFT
Luacopilot · nwdxlgzs
Params596M
Context32K
Q4_K_M0.4 GB
GGUF
DA
DACMini_125M
Dacmini · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
QW
Qwen3 14B Gwb Press Conference Sft Merged
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
QW
Qwen2.5 0.5B Human
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
BA
Baichuan2 7B Chat
Baichuan · mradermacher
Params7.51B
Context4K
Q4_K_M4.6 GB
GGUF
QW
auditbox command guard 0.8b
Qwen · Motanni
Params752M
Context256K
Smallest0.8 GB
ReasoningTool use
QW
Qwen2.5 7B Instruct Uncensored
Qwen · roleplaiapp
Params7.62B
Context32K
Smallest3.0 GB
GGUF
QW
Qwen2.5 7B Instruct Uncensored
Qwen · yemiao2745
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
LL
tamil llama 13b instruct v0.1
Llama · abhinand
Params13.2B
Context4K
Q4_K_M8.0 GB
GGUF
GE
Gemma3 1B gptoss20b Reasoning Distilled
Gemma · generalchucklese
Params1B
Context32K
Q4_K_M0.8 GB
Reasoning
RE
RetroDFM R v0 8B
Retrodfm · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
MIMIC DeepThink 2B
Mimic · mradermacher
Params2.09B
Context8K
Q4_K_M1.4 GB
GGUF
LL
Llama 3 Lunar 8B v0.1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Models Orion Zhen Qwen2.5 7B Gutenberg KTO
Qwen · MaziyarPanahi
Params7.62B
Context32K
Smallest5.3 GB
Tool use
NA
NanoLM 0.3B Instruct v2
Nanolm · mradermacher
Params315M
Context128K
Q4_K_M0.3 GB
Coding
DE
bs_roformer_dereverb_room
Dereverb · thepatch
Params29M
Context—
Smallest0.1 GB
GGUF
QW
auditbox h3c risk 0.8b
Qwen · Motanni
Params752M
Context256K
Smallest0.8 GB
ReasoningTool use
LL
tamil llama 7b instruct v0.1
Llama · abhinand
Params6.87B
Context4K
Q4_K_M4.2 GB
GGUF
OP
OpenVerifiableLLM 23M conversation
Openverifiablellm · AOSSIE
Params35M
Context512
Smallest0.1 GB
Reasoning
LL
Llama 33B Instructed
Llama · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF

Keep browsing