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
AU
AutoCoder
Autocoder · legraphista
Params33.3B
Context16K
Smallest7.2 GB
Coding
QW
Huihui Qwen3.5 9B Abliterated Grimoire SFT
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
CY
Cydonia 24B v4.3
Cydonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QW
Qwen3 VL 8B Instruct Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Huihui Qwen3 VL 8B Thinking Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
ReasoningVision
TU
Turkish Llm 7b Instruct
Turkish · mradermacher
Params7.38B
Context32K
Q4_K_M4.5 GB
Reasoning
SK
sketch
Sketch · calcuis
Params11.9B
Context—
Smallest4.0 GB
GGUF
HU
Humanizer 3B Safetensors
Humanizer · mradermacher
Params3.66B
Context128K
Q4_K_M2.2 GB
GGUF
LU
LunarAI
Lunarai · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
QW
Ektome Qwen3 VL 8Bi PristinelyUncensored
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Qwen2.5 Coder 7B Instruct OBLITERATED Advanced
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
GE
Gemma 4 Giftige Blume 31B v1
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplay
QW
MathSmith Hard Problem Synthesizer Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
GP
Gpt Oss 20b Heretic Distilled MiniMax M2.1
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
CodingTool use
GE
Gemma 3 27b It Abliterated Refined Vision
Gemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Vision
QW
DreamFast Qwen3 8b Heretic
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Coding
LL
Llama 3.1 Taiwan 8B Instruct
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Hamanasu QwQ V1.5 Instruct i1
Qwen · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningRoleplay
GE
Gemma2 27b Swahili It
Gemma · mradermacher
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
KR
Krakowiak 7B v2 i1
Krakowiak · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OH
Ohashi NeMo 12B
Ohashi · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
LT
ltx2
Ltx · gguf-org
Params11.8B
Context128K
Smallest4.8 GB
GGUF
TU
TutorRL 7B
Tutorrl · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
TW
Twisted Cyclone 31B
Twisted · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
GE
Gemma 4 31B Storymaxxed3
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
SU
Sumo T9 7B v0.1 i1
Sumo · mradermacher
Params6.89B
Context4K
Q4_K_M4.2 GB
GGUF
MI
Mirai 70B 2.1
Mirai · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
MI
MIXdevAI yandexGPT5 8B
Mixdevai · mradermacher
Params8.04B
Context32K
Q4_K_M4.9 GB
Tool use
QW
Qwen3.5 9B
Qwen · Zirconium419122
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwen3 MOE 6x6B Star Trek Universe Alpha 256k Ctx 36B
Qwen · mradermacher
Params26.5B
Context256K
Q4_K_M16.1 GB
CodingReasoning

Other quants

Keep browsing