Q2_K_S GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 19715 models have a Q2_K_S file. Sizes run from 2M to 671B parameters. The longest trained context is 10240K tokens.
LL
Higgs-Llama-3-70B
Llama · legraphista
Params70.6B
Context8K
Smallest15.3 GB
MA
Marco DeepResearch 8B
Marco · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
TR
Translategemma 12b It
Translategemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
DE
DeepSeek V2 Lite Chat
DeepSeek · duyntnet
Params15.7B
Context160K
Q4_K_M10.4 GB
GR
Grok Oss Revenant 70B
Grok · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
NE
Nexa AI 4x4B Instruct
Nexa · mradermacher
Params12.1B
Context256K
Q4_K_M7.4 GB
SO
SOLAR 10.7b Ko Y24_v1.0
Solar · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
RO
Rocinante X 12B v1 Absolute Heresy
Rocinante · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
TO
Tower Plus 9B Abliterated Hf Data
Tower · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
QW
Qwen3 30B A3B Instruct 2507 FT
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
NE
NVIDIA-Nemotron-3.5-Bolt-74B-DERISKED
Nemotron · freakyskittle
Params74B
Context1024K
Q4_K_M46.4 GB
OH
Ohm MythosHeretic
Ohm · mradermacher
Params3.09B
Context128K
Q4_K_M1.9 GB
DE
deepseek-coder-6.7b-instruct
DeepSeek · duyntnet
Params6.74B
Context16K
Q4_K_M4.1 GB
QW
Qwen3.8 27B Uncensored Heretic v3
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
FA
Fara TARS 7B
Fara · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
UniReason Qwen3 14B No Think SFT
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
OR
Ornith 1.5 35B A3B 3MPER0RR Abliterated
Ornith · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
LL
Llama 3.1 8B Instruct Abliterated Obliteratus
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
PH
Phi 4 Mini Instruct Abliterated
Phi · Melvin56
Params3.84B
Context128K
Q4_K_M2.5 GB
GE
Gemma 3 12b It Ultra Heretic
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
XW
XwinCoder 7B i1
Xwincoder · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
ME
MenteE Code 3B
Mentee · mradermacher
Params3.09B
Context128K
Q4_K_M1.9 GB
RE
reader lm 0.5b IMat
Reader · legraphista
Params494M
Context250K
Smallest0.3 GB
MI
OpenMath-Mistral-7B-v0.1-hf
Mistral · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
ST
STARK WEB 12B v1.7
Stark · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ZW
ZwZ 7B i1
Zwz · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
Qwen2.5 4x7B Quad Coder Instruct 30B 128k Ctx
Qwen · mradermacher
Params30.4B
Context128K
Q4_K_M18.5 GB
GE
Gemma 4 12B It Esper4
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
QW
Qwen3 4B Uncensored
Qwen · mradermacher
Params4B
Context40K
Q4_K_M2.5 GB
HE
HER 32B
Her · mradermacher
Params32.8B
Context128K
Q4_K_M19.8 GB