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.
MI
Hermes 2 Pro Mistral 7B GodCoder
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GP
Gpt Oss 20b Heretic Ara v3
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
QW
Qwen3 VL 8B Instruct Abliterated v2.0
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
AD
Adversary 8B v1.22
Adversary · mradermacher
Params8.03B
Context1048K
Q4_K_M4.9 GB
QW
rStar Coder Qwen3 0.6B
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
LO
Loyal-Macaroni-Maid-7B
Loyal · duyntnet
Params7.24B
Context8K
Q4_K_M4.4 GB
YI
brucethemoose Yi 34B 200K DARE megamerge v8 iMat
Yi · Nexesenex
Params34.4B
Context195K
Q4_K_M20.7 GB
QW
Meissa Qwen2.5 7B Instruct
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Liujgoj Cantonese Qwen3 8B Instruct
Qwen · mradermacher
Params8.23B
Context32K
Q4_K_M5.1 GB
ER
ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
GE
Gemma 3 12b It Norm Preserved Biprojected Abliterated
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
DE
Qwen2.5 MOE 6x1.5B DeepSeek Reasoning e32 i1
DeepSeek · mradermacher
Params8.71B
Context128K
Q4_K_M5.3 GB
QW
Ostrich 32B Qwen3 251003
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
AL
Almost Human X3 32bit 1839 6B
Almost · mradermacher
Params5.94B
Context256K
Q4_K_M3.6 GB
TU
TutorRL 7B Think
Tutorrl · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
TU
Turkish Llm 14b Instruct
Turkish · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GE
Gemma4 26B A4B Korean Opus 4.6 Distilled
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ZE
Zen3 Nano
Zen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
QW
Qwen3 Shining Lucy CODER 3.5B Brainstorm20x E32
Qwen · mradermacher
Params3.38B
Context40K
Q4_K_M2.1 GB
ME
Medgemma 27b It
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
MA
Matter 0.1 7B Boost
Matter · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
WA
Warlock 7B v3 Uncensored
Warlock · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
DO
Doppelganger Twist 24B
Doppelganger · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
MI
Mistral 2x24B MOE Power Magistral Devstral Reasoning Ultimate 44B
Mistral · mradermacher
Params43.7B
Context128K
Q4_K_M26.5 GB
MA
Mars 27B V.1 Heretic v1.2
Mars · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
DE
Devstral Small 2505 Deepseek V3.2 Speciale Distill
DeepSeek · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
MI
Nexus IKM Hermes 2 Pro Mistral 7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
AU
AutoGLM Phone 9B Multilingual
Autoglm · mradermacher
Params9.4B
Context64K
Q4_K_M6.2 GB
LL
Llama 3 8B Instruct RR Abliterated
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen2.5 14B Instruct Heretic
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB