GGUF models: cc-by-nc-sa-4.0 license

885 GGUF models listed under the cc-by-nc-sa-4.0 license on Hugging Face. Always read the license text before commercial use. Sizes run from 3M to 141B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
TE
T.E 8.1
tensorblock
Params7.62B
Context32K
Smallest3.0 GB
GGUF
LL
llama3 koen sft dpo v1
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
KO
kyujinpy KoT platypus2 7B
Kot · tensorblock
Params6.86B
Context2K
Smallest2.6 GB
GGUF
QW
Sakura-13B-Qwen2beta-v0.9
Qwen · Kunger
Params14.2B
Context32K
Smallest7.8 GB
GGUF
LL
Llama 3 Soliloquy 8B i
Llama · SolidSnacke
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
NorskGPT Llama 13B v0.1
Llama · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
QW
Qwen3 4B Thinking 2507 GRPO Uncensored
Qwen · puwaer
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
CU
Custom KoLLM 13B v2 Q4 K M
Custom · itlwas
Params13.2B
Context2K
Q4_K_M8.0 GB
GGUF
GA
GaLLM multi 14B v0.1
Gallm · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
Tool use
NE
nemotron nano 4b writing style
Nemotron · StratumAnalysisGroup
Params4.51B
Context128K
Q4_K_M2.8 GB
Tool use
SO
SOLAR Tail 10.7B
Solar · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
LL
Kyujinpy PlatYi 34B Llama Q v3
Llama · tensorblock
Params34.4B
Context4K
Smallest12.8 GB
GGUF
MI
OpenLLM France Claire Mistral 7B 0.1
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
QW
Qwen3.8 27B Turkish CPT 1M BF16
Qwen · UgurI
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
DR
DRT O1 7B
Drt · DevQuasar-6
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
TE
NLPark/Test0_SLIDE
Test · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
princip v0.2
Qwen · jolovicdev
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
LL
Llama 3 KoEn 8B Instruct preview
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
CA
CarbonVillain En 10.7B v5
Carbonvillain · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
KY
Kyujinpy PlatYi 34B 200k Q FastChat
Kyujinpy · tensorblock
Params34.4B
Context195K
Smallest12.8 GB
GGUF
BA
BatchOnline GRPO 7B
Batchonline · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
CodingReasoningTool use
CU
Custom KoLLM 13B v2
Custom · tensorblock
Params13.2B
Context2K
Smallest4.9 GB
GGUF
LL
NorskGPT Llama 7B v0.1
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
DE
Dear My best Friends 13B
Dear · tensorblock
Params13B
Context2K
Smallest4.9 GB
GGUF
PR
my private model
Private · theinfamousbanana
Params14.8B
Context128K
Q4_K_M4.9 GB
Tool use
LL
starmpcc Asclepius Llama3 8B
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
QW
yao bao bao8 ALL
Qwen · AngelWarmSmile123
Params7.62B
Context32K
Smallest4.7 GB
ReasoningTool use
EP
256 5epoch i1
Epoch · mradermacher
Params256M
Context2K
Q4_K_M0.2 GB
GGUF
QW
sakura-14b-qwen2.5-v1.0-iq4xs
Qwen · asdasrdqa
Params14.8B
Context128K
Smallest8.2 GB
Tool use
ST
StopCarbon 10.7B v4
Stopcarbon · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF

Keep browsing