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
QW
Qwen3 4b Z Image Turbo AbliteratedV1
Qwen · mradermacher
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
MA
Marco Nano Base
Marco · mradermacher
Params8.16B
Context32K
Q4_K_M5.5 GB
GGUF
QW
CoReward Qwen3 8B Base
Qwen · mradermacher
Params8.19B
Context32K
Q4_K_M5.0 GB
GGUF
GE
Gemma 3 1b It
Gemma · DavidAU
Params1B
Context32K
Q4_K_M1.1 GB
GGUF
ST
StormSeeker 24B v1
Stormseeker · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
ZE
Zen4 Thinking
Zen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
Reasoning
QW
Qwen3 14B Uncensored
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
CO
Control 8B V1.1
Control · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LU
MN 12B LucidFaun RP RU
Lucidfaun · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
GO
Goetia 24B v1.1
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
HU
Hunyuan MT 7B
Hunyuan · mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
TR
Triumvirate Qwopus MiMo Ornith 9B Coder
Triumvirate · pragmaticcs
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoning
RW
RWKV 5.2 3B NSFW Role 16k
Rwkv · mzwing
Params3.1B
Context1024K
Q4_K_M1.9 GB
GGUF
PA
PathfinderAI i1
Pathfinderai · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
AP
Apollo Astralis 4b
Apollo · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
YA
YanoljaNEXT Rosetta 27B 2511
Yanoljanext · mradermacher
Params28.4B
Context128K
Q4_K_M17.3 GB
GGUF
RI
RimDialogue 8B v1 PaperWitch Heresy
Rimdialogue · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
NA
Nanbeige4.2-3B
Nanbeige · Mungert
Params4.17B
Context256K
Q4_K_M2.8 GB
ReasoningTool use
GE
Gemma 3 12b It Biprojected Abliterated
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
QW
Qwen3.5 40B Claude 4.5 Opus High Reasoning Thinking
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
CodingReasoningRoleplay
AY
Ayla Light 12B
Ayla · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CO
Command R 35b Writer v2
Command R · mradermacher
Params35B
Context128K
Q4_K_M21.5 GB
GGUF
OL
Olmo 3 7B RL Zero Code
OLMo · mradermacher
Params7.3B
Context64K
Q4_K_M4.5 GB
CodingReasoning
PL
Plano Orchestrator 30B A3B
Plano · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Tool use
QW
ADAPT Qwen3 8.5B
Qwen · mradermacher
Params8.49B
Context40K
Q4_K_M5.2 GB
ReasoningTool use
MY
MythoMax L2 13b Heretic
Mythomax · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
VI
Video SALMONN 2 Pro 32B
Video · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
GGUF
OM
OmniSQL 32B
Omnisql · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
ZW
ZwZ 8B Heretic
Zwz · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool use
MI
OpenHermes-2.5-Mistral-7B
Mistral · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use

Other quants

Keep browsing