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.
MI
MiniCPM5 2B
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
CE
CeleMo Instruct 128k i1
Celemo · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
OD
Odins Allseeing Eye 9B i1
Odins · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
LL
Llama 3.1 Storm 8B
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
MI
Mistral Small 3.1 24B Base 2503 Hf DanChat
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
UM
CENTAURUS Components v2 i1
Uma · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
DE
Deepseek Coder 1.3b Instruct
DeepSeek · mradermacher
Params1.35B
Context16K
Q4_K_M0.9 GB
OP
OpenElla NovelWriter Requiem
Openella · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
TI
TinyRP 12B
Tinyrp · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
QW
Qwen3.5 9B Ultra Uncensored Heretic v2
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GL
GLM 4.7 Flash
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
CO
CodeScout 14B
Codescout · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
IN
InverseCoder-CL-7B
Inversecoder · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
LL
llama3 42b v0 iMat
Llama · InferenceIllusionist
Params43.2B
Context8K
Q4_K_M26.1 GB
ZU
Zurich 14B GCv2 500k
Zurich · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
MI
Mistral NeMo Minitron 8B Base
Mistral · legraphista
Params8.41B
Context8K
Smallest2.1 GB
JA
Jade 20B
Jade · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
QW
Ideogram 4 Text Encoder Heretic DHQ
Qwen · pottokao
Params8.2B
Context256K
Q4_K_M5.0 GB
SH
L3.3 Shakudo 70b
Shakudo · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
AU
Austral 70B Preview i1
Austral · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
YI
dolphin-2.9.3-Yi-1.5-34B-32k
Yi · bartowski
Params34.4B
Context32K
Q4_K_M20.7 GB
GE
Gemma 4 12b Heretic Styletune Head
Gemma · mradermacher
Params12.9B
Context128K
Q4_K_M7.9 GB
LL
Llama 3 Open Ko 8B i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
QW
Qwen3.5 9B Abliterated v2 MAX
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
FL
Q3.5 9B DS v4 Flash DA
Flash · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
EX
EXAONE Deep 32B
Exaone · bartowski
Params32B
Context32K
Q4_K_M19.3 GB
ST
STARK WEB 12B
Stark · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
MI
Noromaid v0.4 Mixtral Instruct 8x7b Zloss i1
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.9 GB
LL
Llama MagicalGirl i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Hermes-2-Theta-Llama-3-8B
Llama · thesven
Params8B
Context8K
Q4_K_M4.9 GB