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
MI
Minecraftism 4B Thinking Uncensored
Minecraftism · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
SM
Smart Commit 0.5b v0.3
Smart · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
PA
MS3.2 PaintedFantasy Visage v3 34B Ultra Uncensored Heretic
Paintedfantasy · mradermacher
Params34.1B
Context128K
Q4_K_M20.7 GB
Roleplay
JA
Jais Adapted 70b Chat
Jais · mradermacher
Params69.5B
Context4K
Q4_K_M41.8 GB
Coding
QW
Qwen3.8 27B Heretic v2
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
GE
Gemma 4 26B A4B It
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
GE
Gemma 4 19B A4B It The DECKARD Thinking
Gemma · mradermacher
Params18.4B
Context256K
Q4_K_M12.3 GB
CodingReasoningRoleplay
IN
InternVL3_5 8B
Internvl · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Coding
QW
Qwen3 VL Reranker 8B
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
EmbeddingVision
PH
AS Pharade 8B
Pharade · mradermacher
Params8B
Context32K
Q4_K_M4.9 GB
GGUF
GP
Gpt Oss 20b Abliterated
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
XI
XiaoHong v1
Xiaohong · mradermacher
Params8.2B
Context40K
Q4_K_M5.0 GB
GGUF
VI
Vims2 7B
Vims · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
QW
X Coder RL Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen2.5 1.5B Instruct uncensored i1
Qwen · mradermacher
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
QW
Qwen3.6 35B A3B REAM 160 ru agent GGUF MTPLess
Qwen · WaveCut
Params22.6B
Context256K
Q4_K_M13.8 GB
GGUF
ME
MetaStone S1 32B
Metastone · mradermacher
Params32.8B
Context40K
Q4_K_M19.9 GB
GGUF
MO
Moonlight 16B A3B Instruct Bruno
Moonlight · mradermacher
Params16B
Context8K
Q4_K_M10.5 GB
GGUF
GE
Gemma 3 12b It Jailbreak ES
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
MI
Magistral Small 2506
Mistral · mradermacher
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
OC
OceanGPT Basic 7B
Oceangpt · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
GP
Gpt Oss 20b Heretic v3
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
HU
Huihui MiroThinker v1.5 30B Abliterated
Huihui · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool use
SU
Sugoi 14B Ultra HF
Sugoi · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
GL
GLM 4.7 Flash REAP 23B A3B absolute heresy i1
GLM · mradermacher
Params23B
Context198K
Q4_K_M13.9 GB
GGUF
MI
MiniCPM5 2B
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
ReasoningTool use
MI
Mistral Small 3.1 24B Base 2503 Hf DanChat
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
UM
CENTAURUS Components v2 i1
Uma · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OP
OpenElla NovelWriter Requiem
Openella · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
TI
TinyRP 12B
Tinyrp · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay

Other quants

Keep browsing