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
Melinoe Next 80B A3B Thinking Diluted v0
Melinoe · mradermacher
Params79.7B
Context256K
Q4_K_M48.4 GB
ReasoningTool use
LF
LFM2 12B A1B SpeedDemon High Intelligence Series B
Lfm · mradermacher
Params11.3B
Context125K
Q4_K_M6.8 GB
GGUF
GO
Goose 7.2B G1k 20261011
Goose · mradermacher
Params7.2B
Context1024K
Q4_K_M4.5 GB
GGUF
GL
LFM2 8B A1B GLM 4.7 Flash Thinking Quantum IQ1C
GLM · mradermacher
Params8.34B
Context125K
Q4_K_M5.0 GB
CodingReasoningRoleplay
ZW
ZwZ 8B i1
Zwz · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool use
GE
Gemma 3 12b It Ultra Uncensored Heretic
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
CO
Corridor C 12B
Corridor · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
LF
LFM2.5 350M Uncensored
Lfm · mradermacher
Params354M
Context125K
Q4_K_M0.2 GB
GGUF
QW
Qwen3.5 35B A3B
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
AL
G4 Alice v1.1 31B
Alice · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
PA
MS3.2 PaintedFantasy v4.1 24B Heretic v2
Paintedfantasy · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingRoleplay
CO
Convergent 7B
Convergent · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
AR
Arxh 2.29 12B It
Arxh · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
QW
Qwen3 EZO 8B YOYO Nuslerp Plus 128K
Qwen · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
GGUF
QW
Qwen3 4B Esper3
Qwen · mradermacher
Params4B
Context40K
Q4_K_M2.5 GB
CodingReasoning
QW
Qwen3 VL 32B Thinking
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
ReasoningVision
CA
Carnice V2 27b
Carnice · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
QW
Qwen3 VL 32B Instruct
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
Tool useVision
LL
Llama 3.2 4X3B MOE Ultra Instruct 10B
Llama · mradermacher
Params9.95B
Context128K
Q4_K_M6.1 GB
Tool use
AD
AdQWENistrator 9B
Adqwenistrator · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
GL
Gliese OCR 7B Post1.0
Gliese · prithivMLmods
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
GO
Goetia 26B A4B v1.4
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
NO
Nous Hermes ReflexAgent 8B v1
Nous · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
VE
MN VelvetCafe RP 12B V2
Velvetcafe · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
NA
NaNovel 27B
Nanovel · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
QW
Qwen2.5 Coder 7B Instruct
Qwen · legraphista
Params7.62B
Context32K
Smallest1.9 GB
CodingTool use
KA
KAT V1 40B
Kat · mradermacher
Params40.6B
Context128K
Q4_K_M24.6 GB
Tool use
HO
Holo 3.1 9B Coder
Holo · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
LL
Wayfarer Large 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
ES
Estopia 13B 32k
Estopia · mradermacher
Params13B
Context32K
Q4_K_M7.9 GB
GGUF

Other quants

Keep browsing