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.
CA
Calme-7B-Instruct-v0.5
Calme · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.5 2B Polaris HighIQ INSTRUCT
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
QW
heretic_EVA Qwen2.5 1.5B v0.0
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
LL
Gemma 2 Llama Swallow 9b It v0.1 Heretic
Llama · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
LU
Lucent Witch 31B
Lucent · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
AF
Africlaude 7B i1
Africlaude · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Qwen3.5 4B Claude 4.6 HighIQ THINKING
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
MI
Devstral Small 2507 Rebased Vision
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
QW
Qwen3 Yoyo V4 42B A3B Thinking TOTAL RECALL PDK V
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
QW
Compumacy Experimental 32B
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
IM
Impish_Bloodmoon_12B_Abliterated
Impish · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
SO
SOLAR-10.7B-Instruct-v1.0
Solar · duyntnet
Params10.7B
Context4K
Q4_K_M6.5 GB
ME
MedSwin 7B KD i1
Medswin · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
PE
Percival 01 7b slerp i1
Percival · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.5 22B A3B Heretic Reap
Qwen · mradermacher
Params22.2B
Context256K
Q4_K_M13.6 GB
ST
Step 3.5 Flash REAP 121B A11B i1
Step · mradermacher
Params121B
Context256K
Q4_K_M72.8 GB
PA
PathFinderAI4.0 i1
Pathfinderai · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
MY
MythoMax-L2-13b
Mythomax · duyntnet
Params13B
Context4K
Q4_K_M7.9 GB
QW
Qwen3.5 4B Heretic
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
QW
Ektome Qwen2.5 Coder 14B Instruct PristinelyUncensored
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
MO
Morbid Miasma 24B
Morbid · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
LL
Meta Llama 3.1 8B Instruct
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
VI
MN Violet Lotus 12B Heretic
Violet · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
LL
Llama3.1 8b Cpt Sea Lionv3 Instruct
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
BL
Q3.5 BlueStar v2 27B Ultra Uncensored Heretic v1
Bluestar · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
LU
Lucie 7B GRPO Science 500
Lucie · mradermacher
Params6.71B
Context31K
Q4_K_M4.1 GB
OP
OpenSeeker v1 30B SFT
Openseeker · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen2.5 Math 1.5B Instruct
Qwen · legraphista
Params1.54B
Context4K
Smallest0.4 GB
WA
Walnoot 8b Instruct
Walnoot · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
JA
Jais Adapted 70b
Jais · mradermacher
Params69.5B
Context4K
Q4_K_M41.8 GB