IQ2_S GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 26079 models have a IQ2_S file. Sizes run from 2M to 1030B parameters. The longest trained context is 10240K tokens.
QW
Qwen3.5 27B Deckard PKD Heretic Uncensored Thinking
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
DA
L3 Dark Planet Horror City 8B NEO Imatrix
Dark · DavidAU
Params8B
Context8K
Q4_K_M4.9 GB
TU
Turbo Ai 7b
Turbo · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
NE
Neuraltranslate 27b Mt Nah Es v1
Neuraltranslate · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
RE
Rei 12B V3 Base
Rei · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
VE
Veloxy 1B
Veloxy · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
CA
CARA Sage 24B
Cara · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
PE
PersonaVLM
Personavlm · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GL
GLM 4.7 Flash Derestricted
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
AU
Aura-Uncensored-OAS-8B-L3
Aura · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
CY
CyberPal-2.0-20B
Cyberpal · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
PI
PiVoT SUS RP i1
Pivot · mradermacher
Params34.4B
Context8K
Q4_K_M20.7 GB
CH
chronoboros 33B i1
Chronoboros · mradermacher
Params32.5B
Context2K
Q4_K_M19.9 GB
MI
Devstral Small 2507 Vision
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
QW
Qwen3.5 9B Deckard Claude DIMOE Uncensored Heretic Thinking
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
XW
Xwinter 120b i1
Xwinter · mradermacher
Params118B
Context4K
Smallest25.0 GB
LL
Meta Llama 3.1 70B Instruct
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
YO
Youri 7b Chat
Youri · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
YA
YanoljaNEXT Rosetta 12B 2510
Yanoljanext · bartowski
Params12.8B
Context128K
Q4_K_M7.9 GB
CO
CoT 2.5 i1
Cot · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
AL
Alpacino30b i1
Alpacino · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
LL
LongWriter Llama3.1 8b
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
NE
nvidia OpenCodeReasoning Nemotron 14B
Nemotron · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
LL
Replete-Coder-Llama3-8B
Llama · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
CY
CyberOss 2.0 20B i1
Cyberpal · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GL
GLM 4.5 Iceblink v3 106B A12B
GLM · mradermacher
Params107B
Context128K
Q4_K_M70.4 GB
QW
Qwen3.5 9B Claude 3xMerge UNCENSORED Heretic
Qwen · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
QW
Rombo LLM V3.0 Qwen 32b
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
AY
Aya Expanse 32b
Aya · bartowski
Params32.3B
Context8K
Q4_K_M19.8 GB
LL
NPO SAM WMDP llama3 8b instruct i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB