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.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 14B Instruct 1M
Qwen · bartowski
Params14.8B
Context986K
Q4_K_M9.0 GB
GGUF
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
DA
Dans PersonalityEngine V1.3.0 24b
Dans · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingRoleplay
GR
Granite 20b Code Instruct 8k
Granite · mradermacher
Params20B
Context8K
Q4_K_M12.8 GB
CodingTool use
QU
QuartetAnemoi 70B t0.0001
Quartetanemoi · backyardai
Params69B
Context32K
Q4_K_M41.4 GB
GGUF
GR
Granite 8b Code Base 128k
Granite · mradermacher
Params8.05B
Context125K
Q4_K_M4.9 GB
Coding
QW
Qwen3.8-27B
Qwen · Aleks199999
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
PA
Pantheon Reasoning 26B A4B 1.1 V2
Pantheon · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplay
NE
nexus medical
Nexus · King3Djbl
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
DE
DeepSeek V4 Flash 0731
DeepSeek · AtomicChat
Params284B
Context1024K
Smallest70.2 GB
ReasoningTool use
QW
Qwen3.8-27B
Qwen · kcarly
Params27.3B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
MI
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
DA
PocketDoc Dans PersonalityEngine V1.2.0 24b
Dans · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
CodingRoleplay
MI
MiniCPM5 1B
MiniCPM · NANI-Nithin
Params1.08B
Context128K
Q4_K_M0.7 GB
GGUF
GE
Gemma 4 26B A4B It Abliterated
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
QW
Qwen3.8-27B
Qwen · Fhjdjdbxhshsh
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
QW
Qwen3-Coder-Next
Qwen · Mungert
Params79.7B
Context256K
Q4_K_M49.2 GB
CodingTool use
QW
Qwen3 VL 8B Abliterated Caption It
Qwen · prithivMLmods
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
MA
Magidonia 24B v4.3 Heretic v1.2
Magidonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QW
Qwen3.5 27B Uncensored Heretic v1
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
PR
PreciseCoder 27B
Precisecoder · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Coding
QW
Qwen2.5 0.5B Instruct
Qwen · ThomasBaruzier
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
PH
dolphin-2.9.2-Phi-3-Medium-abliterated
Phi · mradermacher
Params14B
Context4K
Q4_K_M8.4 GB
CodingTool use
QW
QwQ 32B
Qwen · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
MI
MiMo Negentropy 9B AGSI
Mimo · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
XL
xLAM 8x7b R
Xlam · legraphista
Params46.7B
Context32K
Smallest9.8 GB
Tool use
LL
Llama 3.3 70B Instruct Abliterated v2
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
MA
L3.3 70B Magnum v4 SE
Magnum · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
WI
Wicked Tutu 26B A4B Final
Wicked · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
PR
Prentis EQ 2
Prentis · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Reasoning

Other quants

Keep browsing