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
PE
Pebble 1 30B
Pebble · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
ReasoningTool use
SA
Salamandra 7b Instruct Uncensored Abliterated
Salamandra · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
AF
AfriqueQwen3.5 9B 50Langs
Afriqueqwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
GE
Gemma 4 12B It Tachibana Agent
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
CodingReasoning
EE
EEVE Instruct Math 10.8B i1
Eeve · mradermacher
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
OP
OpenElla NovelWriter 8B V2 Merged
Openella · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
BI
Bielik Minitron 7B v3.0 Instruct Heretic
Bielik · mradermacher
Params7.48B
Context32K
Q4_K_M4.5 GB
GGUF
QW
Qwen2.5 VL 3B Instruct Unredacted MAX
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
MI
MiniCPM5 1B
MiniCPM · mradermacher
Params1.08B
Context128K
Q4_K_M0.7 GB
Tool use
RY
RynnBrain CoP 8B
Rynnbrain · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingVision
MO
L3 MOE 4x8B Dark Planet Rising 25B i1
Moe · mradermacher
Params25B
Context8K
Q4_K_M15.2 GB
GGUF
QW
Carnice Qwen3.6 MoE 35B A3B
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Tool use
TI
Tifa DeepsexV2 7b MGRPO Safetensors
Tifa · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Roleplay
QW
Huihui Qwen3.5 4B Claude 4.6 Opus Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
Reasoning
BA
L2 7b Base Guanaco Uncensored i1
Base · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
ZE
zephyr-7b-sft-full-SPIN-iter3
Zephyr · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
HU
Huihui MiroThinker v1.0 8B Abliterated
Huihui · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
GGUF
QW
Qwen3 Yoyo V3 42B A3B Thinking TOTAL RECALL Horror
Qwen · mradermacher
Params42.4B
Context986K
Q4_K_M25.7 GB
CodingReasoning
NE
OpenMath Nemotron 14B Kaggle
Nemotron · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
QW
Qwen2.5 1.5B
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Qwen2.5 14B Instruct 1M
Qwen · duyntnet
Params14.8B
Context986K
Q4_K_M9.0 GB
GGUF
GE
Gemma 4 12B Coder Fable5 Composer2.5 v1
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
CodingReasoning
GE
Gemma4 Gutenberg 31B Heretic
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
GE
Gemma 4 12b Blorbo
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
Roleplay
GR
Granite 4.2 8b Heretic
Granite · mradermacher
Params8.79B
Context128K
Q4_K_M5.3 GB
ReasoningTool use
HU
Huihui LFM2 24B A2B Abliterated
Huihui · mradermacher
Params23.8B
Context125K
Q4_K_M14.4 GB
GGUF
HE
Hermes 4 14B OBLITERATED
Hermes · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
Tool use
QW
Qwen3.5 2B Base
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 8B RP v0.1
Qwen · Aratako
Params8.19B
Context40K
Q4_K_M5.0 GB
Roleplay
IN
Spatial SSRL 7B
InternLM · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF

Other quants

Keep browsing