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.
TI
TinyR1 32B Preview v0.2
Tinyr · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
DA
PocketDoc Dans SakuraKaze V1.0.0 12b
Dans · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
TO
Tongyi-DeepResearch-30B-A3B
Tongyi · Mungert
Params30.5B
Context128K
Q4_K_M19.0 GB
QW
EgoActor 8b Qwen3VL
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · duyntnet
Params1.54B
Context32K
Q4_K_M1.0 GB
CO
Codegemma 7b
Codegemma · mradermacher
Params8.54B
Context8K
Q4_K_M5.3 GB
FO
Foundation Sec 1.1 8B Instruct
Foundation · mradermacher
Params8.03B
Context64K
Q4_K_M4.9 GB
GL
Qwopus GLM 18B Healed
GLM · mradermacher
Params15.9B
Context256K
Q4_K_M9.8 GB
GE
Gemma 4 26B A4B It Arli
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
BO
boto-27B
Boto · mradermacher
Params27.2B
Context8K
Q4_K_M16.6 GB
FL
Aurostral Small
Flamguard · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
YI
Nous-Hermes-2-Yi-34B
Yi · duyntnet
Params34.4B
Context4K
Q4_K_M20.7 GB
QW
Vikhr-Qwen-2.5-1.5B-Instruct
Qwen · Vikhrmodels
Params1.54B
Context32K
Q4_K_M1.0 GB
LL
Llama 3 8b Dolphin Uncensored
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
QW
Qwen3-Reranker-4B
Qwen · Mungert
Params4B
Context40K
Q4_K_M2.5 GB
FR
Franqwenstein 35b
Franqwenstein · mradermacher
Params34.7B
Context128K
Q4_K_M21.0 GB
HY
Hy MT2 30B A3B
mradermacher
Params30B
Context256K
Q4_K_M18.2 GB
CO
c4ai-command-r-v01
Command R · qwp4w3hyb
Params35B
Context128K
Q4_K_M21.5 GB
QW
Community Blend Qwen3 8b
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CA
CADD Base 7B
Cadd · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GE
Gemma 2 2b It
Gemma · ThomasBaruzier
Params2.61B
Context8K
Q4_K_M1.7 GB
MI
Mistral-7B-Instruct-v0.3
Mistral · mmnga
Params7.25B
Context32K
Q4_K_M4.4 GB
LL
Llama 3.X Workout 70B i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RE
Redemption_Wind_24B
Redemption · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
QW
Qwen2.5 2X11B CODER Dueling Wolverines V2 28B
Qwen · mradermacher
Params28B
Context32K
Q4_K_M17.0 GB
VE
Vecteus v1
Vecteus · mmnga
Params7.24B
Context4K
Q4_K_M4.4 GB
LL
gpt 4o distil Llama 3.1 8B Instruct PaperWitch heresy i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
LL
Medichat Llama3 8B i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
LL
Pantheon-RP-1.0-8b-Llama-3
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
EU
L3.3 70B Euryale v2.3 Heretic
Euryale · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB