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.

Most downloadedNewestLargestLongest contextSmallest
ME
Menage 12B
Menage · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
LL
Citrus1.0 Llama 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
PE
Peach 2.0 9B 8k Roleplay Heretic
Peach · mradermacher
Params8.83B
Context16K
Q4_K_M5.3 GB
Roleplay
MI
MiroThinker 1.7 Mini
Mirothinker · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
RI
RigoChat 7b v2
Rigochat · IIC
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen3.6 40B Claude 4.6 Opus Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
CodingReasoningRoleplay
GU
Gumini 1.5B Base i1
Gumini · GuminiResearch
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
MARTHA 73B Qwen2 VL i1
Qwen · mradermacher
Params72.7B
Context125K
Q4_K_M47.4 GB
Vision
EU
EuroLLM 9B Instruct Heretic
Eurollm · mradermacher
Params9.15B
Context4K
Q4_K_M5.6 GB
Roleplay
QW
Huihui Qwen3 4B Instruct 2507 Abliterated
Qwen · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
QW
Qwen3.5 27B Deckard PKD Heretic Uncensored Thinking
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplay
DA
L3 Dark Planet Horror City 8B NEO Imatrix
Dark · DavidAU
Params8B
Context8K
Q4_K_M4.9 GB
Roleplay
TU
Turbo Ai 7b
Turbo · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
NE
Neuraltranslate 27b Mt Nah Es v1
Neuraltranslate · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
RE
Rei 12B V3 Base
Rei · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
VE
Veloxy 1B
Veloxy · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
CA
CARA Sage 24B
Cara · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
PE
PersonaVLM
Personavlm · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
GL
GLM 4.7 Flash Derestricted
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
CY
CyberPal-2.0-20B
Cyberpal · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
MI
Devstral Small 2507 Vision
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingVision
QW
Qwen3.5 9B Deckard Claude DIMOE Uncensored Heretic Thinking
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplay
CY
CyberOss 2.0 20B i1
Cyberpal · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
GL
GLM 4.5 Iceblink v3 106B A12B
GLM · mradermacher
Params107B
Context128K
Q4_K_M70.4 GB
Roleplay
QW
Qwen3.5 9B Claude 3xMerge UNCENSORED Heretic
Qwen · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
CodingReasoningTool use
LL
NPO SAM WMDP llama3 8b instruct i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
MI
MiLMMT 46 12B v1.0
Milmmt · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
QW
Hemlock Qwen2.5 Coder 14B
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Coding
QW
Qwopus3.6 27B v1 Preview
Qwopus · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningVision
QV
QVikhr 3 8B Instruction
Qvikhr · Vikhrmodels
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use

Other quants

Keep browsing