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
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
TA
UI-TARS-1.5-7B
Tars · Mungert
Params7.6B
Context125K
Q4_K_M4.8 GB
Vision
GE
Gemma 4 26B A4B It Ultra Uncensored Heretic
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
LL
Llama3.3 8B Instruct Thinking Heretic Uncensored Claude 4.5 Opus High Reasoning
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplay
LL
Meta-Llama-3-70B-Instruct-abliterated-v3.5
Llama · legraphista
Params70.6B
Context8K
Smallest15.3 GB
GGUF
QW
Qwen3.8 27B Heretic JP Roleplay NSFW DanbooruTags
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
Qwen2.5-VL-3B-Instruct
Qwen · Mungert
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
TE
TerminalHorizon 122B A10B
Terminalhorizon · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
GGUF
GE
Gemma 4 31B It The DECKARD HERETIC UNCENSORED Thinking
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
CodingReasoningRoleplay
QW
Qwen3.5 Text 9B NSFW RP RolePlay
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Roleplay
GR
Grok 1
Grok · Arki05
Params316B
Context8K
Smallest65.3 GB
GGUF
QW
Huihui Qwen3 30B A3B Instruct 2507 Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
CY
Blackfrost-AI/CYBER-FROST-3.8-BF16
Cyber · freakyskittle
Params177B
Context256K
Q4_K_M2.6 GB
Vision
QW
SpaceTimee/Suri-Qwen-3.8-27B-Uncensored
Qwen · SpaceTimee
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3 0.6b Abliterated
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
OR
Ornith 1.5 9B Heretic v2
Ornith · Thunder13240
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningVision
MU
Muse Glimmer 30B Heretic Uncensored
Muse · 0bserverx
Params28B
Context128K
Q4_K_M16.9 GB
Vision
QW
Qwen3 0.6B Heretic Heresy Edition
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
DI
Dirty Muse Writer v01 Uncensored Erotica NSFW i1
Dirty · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
NE
NeoHorse-1-4B
Neohorse · ngquocvinh
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
QW
Qwen3 0.6B Heretic Abliterated Uncensored
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
QW
Qwen2.5 Coder 32b Instruct Heretic Sft
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Coding
QW
Huihui Qwen3 VL 30B A3B Instruct Abliterated
Qwen · noctrex
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
QW
Qwen3.6 35B A3B Uncensored Heretic
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
ME
G4 MeroMero 26B A4B It Uncensored Heretic
Meromero · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
QW
Huihui Qwen3.5 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
Therapy 3.8
Qwen · Verdugie
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use

What is Q2_K_S?

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

19,715 models have a Q2_K_S file on ggufmodels.com, and those files range from 0.0 to 225.6 GB. The most downloaded are Cyber Ornith 1.5 9B OBLITERATED, UI-TARS-1.5-7B and Gemma 4 26B A4B It Ultra Uncensored Heretic. For a longer explanation of every quant type, read GGUF quantization explained.

Frequently asked questions

What is Q2_K_S in GGUF?

A GGUF quantization format. Lower numbers mean smaller files and more quality loss.

Should I use Q2_K_S?

Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

How big is a Q2_K_S file?

Q2_K_S files on this site range from 0.0 to 225.6 GB, depending on the model.

Other quants

Keep browsing