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
Qwen3.6 27B Heretic2 Uncensored Finetune Thinking
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplay
HE
Hexis-Pure-Soul-24B
Hexis · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
QW
Hemlock Qwen2.5 Coder 7B
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
HI
Hiber Multi 10B Instruct
Hiber · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
KO
KoSOLRA 10.7B merge v2.2 i1
Kosolra · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
QW
Qwen3 VL 8B Thinking Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
ReasoningTool useVision
SK
Skyfall 31B v4.2
Skyfall · mradermacher
Params31.4B
Context128K
Q4_K_M19.0 GB
Tool use
QW
SvS Qwen Code 7B
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
DO
DocWain 14B v2 Unified
Docwain · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
DO
Doujinshi 14b Instruct
Doujinshi · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
Tool use
FI
FIPO_32B
Fipo · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
Tool use
QW
Qwen3.5 4B SOMPOA Heresy v2
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
QW
CriticLeanGPT Qwen3 14B RL
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
QW
Qwen3 53B A3B 2507 TOTAL RECALL v2 MASTER CODER
Qwen · mradermacher
Params53B
Context256K
Q4_K_M32.1 GB
CodingReasoningTool use
LL
naps llama 3 1 8b instruct v01 i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen3 Shining Lucy CODER 3.4B Brainstorm20x E32
Qwen · mradermacher
Params3.38B
Context40K
Q4_K_M2.1 GB
CodingReasoningTool use
IN
InternVL2_5 78B
Internvl · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool use
AP
Apollo 1 8B
Apollo · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
GE
Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking
Gemma · mradermacher
Params40B
Context128K
Q4_K_M24.5 GB
CodingReasoningRoleplay
ON
Oneirogen 7B Abominable Heresy
Oneirogen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
MI
G4 Midnight Macaw 26B A4B
Midnight · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
KO
Koala 7B HF
Koala · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
GE
Gemma 4 12b It Abliterated
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
GE
Survival Uncensored Gemma 270m v2
Gemma · mradermacher
Params268M
Context32K
Q4_K_M0.3 GB
Roleplay
SC
Scifi Roleplay 24B v1.0
Scifi · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
MA
marin 8b instruct i1
Marin · mradermacher
Params8B
Context4K
Q4_K_M4.9 GB
Reasoning
AS
Astra v1 12B i1
Astra · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GE
Gemma 4 12b Asterion Agentic
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
Tool use
XO
XORTRON.CriminalComputing.2026.27B.Instruct.NEXT
Xortron · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
QW
Qwen3 VL 235B A22B Thinking Heretic
Qwen · mradermacher
Params235B
Context256K
Q4_K_M142.2 GB
ReasoningTool useVision

Other quants

Keep browsing