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
GE
Gemma4 E4B It Disinhibited
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
ReasoningTool use
QW
RC Qwen2VL 7b i1
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
HE
Hexoteric 7B imatrix
Hexoteric · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GP
ANITA NEXT 20B Gpt Oss ITA
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
ReasoningTool use
DR
Dream Coder v0 Instruct 7B
Dream · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
IN
InSight Doc 8B
Insight · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Qwen3 14B Esper3Grayline
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoningTool use
QW
Hemlock Qwen2.5 Coder 32B
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingTool use
NE
neo 7b IMat
Neo · legraphista
Params7.79B
Context8K
Smallest1.7 GB
GGUF
MI
Ministral 3 8B Reasoning 2512 Uncensored
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool useVision
AS
Asterias v73
Asterias · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MI
MiMo VL 7B RL 2508
Mimo · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Tool useVision
QW
DAT Qwen2.5 14B Instruct
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
ST
E Star 12B Base
Star · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
GL
GLM 4.7 Flash Ultra Uncensored Heretic
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
HU
Huihui Fara 7B Abliterated
Huihui · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
RA
RACRO 7B CRO GRPO
Racro · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningTool use
AV
AVAR Thinker 7B
Avar · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Reasoning
DA
Darklit Maiden 12B
Darklit · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
GE
Gemma3 Code Reasoning 4B
Gemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
CodingReasoning
QW
CriticLeanGPT Qwen2.5 32B Instruct SFT RL
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
CO
C4Ai Command R7B 12 2024 Heretic
Command R · mradermacher
Params8B
Context129K
Q4_K_M5.1 GB
Roleplay
DE
DeepSeek R1 Distill Qwen 14B Uncensored Reasoner
DeepSeek · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
BE
Behemoth 128B v3
Behemoth · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
ReasoningTool use
QW
Qwen3 VL 30B A3B Thinking
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool useVision
QW
SAGE MM Qwen2.5 VL 7B SFT_RL
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Huihui Qwen3 Omni 30B A3B Captioner Abliterated
Qwen · mradermacher
Params30.5B
Context64K
Q4_K_M18.6 GB
ReasoningTool use
ZE
Zeta 30b A3B
Zeta · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Tool use
QW
OpenYourMind Qwen3.6 35B A3B Kuato DPO Abliterated Uncensored
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
ED
EdgeRunner Command AgentF 27 12 sonnet i1
Edgerunner · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF

Other quants

Keep browsing