Q3_K_S GGUF models
3-bit k-quant, small. Small files with noticeable quality loss. 102724 models have a Q3_K_S file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.
GL
Huihui GLM 4.6V Flash Abliterated
GLM · mradermacher
Params9.4B
Context128K
Q4_K_M6.2 GB
QW
Bella Bartender Qwen3 1.7b
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
GM
GmshNet 8B v0.1
Gmshnet · hexera-org
Params7.62B
Context32K
Q4_K_M4.7 GB
CH
ChemLLM 20B Chat DPO
Chemllm · mradermacher
Params19.9B
Context32K
Q4_K_M12.0 GB
MI
dolphin 2.8 mistral 7b v02
Mistral · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Models Qwen Qwen2 Math 7B Instruct
Qwen · MaziyarPanahi
Params7.62B
Context4K
Q4_K_M4.7 GB
GE
Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking
Gemma · mradermacher
Params18.4B
Context256K
Q4_K_M12.3 GB
NE
NeuralStar_FusionWriter_4x7b
Neuralstar · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
LL
Replete Coder V2 Llama 3.1 8b
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
WI
wizardlm_wizardcoder-python-7b-v1.0
Wizardlm · TheBloke
Params6.74B
Context16K
Q4_K_M4.1 GB
MI
teknium_hermes-trismegistus-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
Chinese Mistral 7B Instruct v0.1
Mistral · RichardErkhov
Params7.5B
Context32K
Q4_K_M4.5 GB
GP
Gpt Neox 20b
Gpt · mradermacher
Params20.6B
Context2K
Q4_K_M13.1 GB
LL
Llama3.3 8B Instruct Thinking Claude 4.5 Opus High Reasoning
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
RP
RPBizkit v11 12B Base
Rpbizkit · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
YI
Yi 1.5 9B Chat 16K Abliterated
Yi · mradermacher
Params8.83B
Context16K
Q4_K_M5.3 GB
MI
fpham_generate_question_mistral_7b
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
HO
K2-Horizon-375B-A23B
Horizon · bartowski
Params379B
Context512K
Q4_K_M237.8 GB
SP
Spark X2.6 1.7B
Spark · mradermacher
Params1.71B
Context1024K
Q4_K_M1.1 GB
NA
calderaai_naberius-7b
Naberius · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
WI
WizardCoder Python 34B V1.0 i1
Wizardcoder · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
LL
Llama 3 Patronus Lynx 8B Instruct
Llama · QuantFactory
Params8B
Context8K
Q4_K_M4.9 GB
HO
HornyEchidna 13B v0.1
Hornyechidna · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GP
Jinx Gpt Oss 20b
gpt-oss · Jinx-org
Params20.9B
Context128K
Q4_K_M15.8 GB
QW
Qwen 3.8 27b Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
MI
Mixtral 8x7B Instruct v0.1
Mistral · MaziyarPanahi
Params46.7B
Context32K
Q4_K_M28.4 GB
MI
Mistral Nemo Instruct 2407 Absolute Heresy
Mistral · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
NO
Nova-1.1-0.8B
Nova · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
S1
S1 VL 32B
mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
FI
Fimbulvetr 40 i1
Fimbulvetr · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB