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.
LU
Lucid Shadow 31B
Lucid · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
CO
Yi Coder 9B Chat
Coder · legraphista
Params8.83B
Context128K
Smallest2.0 GB
SY
SynLogic 7B Sft Gold v1
Synlogic · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
LL
Llama 3.2 SUN HDIC 1B Instruct
Llama · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
PL
Plesio 70B
Plesio · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
FS
FsfairX-Zephyr-Chat-v0.1
Fsfairx · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.5 2B EmperoAI Qwen3.8 Distill Heretic Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
AS
Asclepio 8B
Asclepio · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
CR
Crow 9B HERETIC 4.6
Crow · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
DE
DeepSeek R1 Distill Qwen 8B Abliterated
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
SU
Supertron1 8B
Supertron · mradermacher
Params8.19B
Context32K
Q4_K_M5.0 GB
GE
L3.3 GeneticLemonade Unleashed 70B i1
Geneticlemonade · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GO
Goetia 24B v1.3 Absolute Heresy
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
QW
Qwen3 VL 32B Thinking Abliterated
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
OC
OctoThinker 8B Short Base
Octothinker · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
NE
NemoAurora RP 12B
Nemoaurora · Aratako
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Qwen3 14B Heretic
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
QW
Qwen2.5 VL 7B NSFW Caption V3 Abliterated
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
TR
Triangulum v2 10B
Triangulum · mradermacher
Params10.3B
Context32K
Q4_K_M6.3 GB
PH
dolphin-2.9.2-Phi-3-Medium-abliterated
Phi · legraphista
Params14B
Context4K
Smallest3.1 GB
RE
reader lm 1.5b IMat
Reader · legraphista
Params1.54B
Context250K
Smallest0.4 GB
LL
Llama-3-8B-Synthia-v3.5
Llama · duyntnet
Params8.03B
Context8K
Q4_K_M4.9 GB
SI
UI Simulator R Web i1
Simulator · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GP
Gpt Oss 120b Heretic v1
gpt-oss · mradermacher
Params117B
Context128K
Q4_K_M87.9 GB
LL
Meta Llama 3.1 8B Instruct
Llama · brittlewis12
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
Qwen2.5-VL-72B-Instruct
Qwen · Mungert
Params73B
Context125K
Q4_K_M47.7 GB
MI
Mistral Helcyon Mercury 12b v3.2 Absolute Heresy
Mistral · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
QW
Qwen3 8B ShiningValiant3
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
LI
LishizhenGPT
Lishizhengpt · mradermacher
Params8.1B
Context2K
Q4_K_M5.3 GB
QW
Soar Qwen 7b
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB