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
GE
Gemma2 9b WangchanLIONv2 instruct i1
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
Gemma 3 12b It Heretic X
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
QW
Qwen3.5 27B Heretic
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Coding
LL
Llama Poro 2 8B Long Base
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Coding
EV
EverythingLM 13b V2 16k
Everythinglm · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
GGUF
QW
Qwen2.5 72B Instruct Heretic
Qwen · brindusa
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
DE
DeepSeek V2 Lite Instruct Abliterated 15 1.2
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
GGUF
NE
neo_7b_sft_v0.1
Neo · legraphista
Params7.79B
Context8K
Smallest1.7 GB
GGUF
QW
Qwen3 16B A3B Abliterated
Qwen · mradermacher
Params16B
Context40K
Q4_K_M9.8 GB
ReasoningTool use
QW
Qwen2.5 72B Instruct Abliterated
Qwen · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
QW
Qwen3 8B HoneyBadger EXP
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
LL
UserLM-8b
Llama · Mungert
Params8.03B
Context8K
Q4_K_M5.3 GB
GGUF
AN
AntAngelMed
Antangelmed · mradermacher
Params103B
Context32K
Q4_K_M62.4 GB
GGUF
HY
HydraCoder i1
Hydracoder · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
KU
Kunoichi-DPO-v2-7B
Kunoichi · duyntnet
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
GE
Gemma4 Garnet 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
AT
OS Atlas Pro 7B
Atlas · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
GL
GLM 4.7 Flash Impotent Heresy
GLM · mradermacher
Params29.9B
Context198K
Q4_K_M18.1 GB
ReasoningTool use
SC
Scal-lite-60b-code-math
Scal · mradermacher
Params73.8B
Context128K
Q4_K_M55.5 GB
CodingTool use
QW
Huihui Qwen3.5 9B Abliterated Grimoire DPO
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
GE
Gemma 4 12B It Heretic_Decensored
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
MU
Muse Glimmer 30B Esper4
Muse · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
CodingReasoningTool use
MU
Muslim 6B V1.0
Muslim · mradermacher
Params5.94B
Context256K
Q4_K_M3.7 GB
Tool use
LL
Dirty Alice RP NSFW Llama 3.2 1B
Llama · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
Roleplay
NE
NeoHorse 1 4B Max Heretic Uncensored TURBO
Neohorse · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
Tool use
MI
Mistral Nemo Instruct 2407 12B Thinking HI Claude Opus High Reasoning
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
QW
Qwen2.5 32B Instruct
Qwen · legraphista
Params32.8B
Context32K
Smallest7.3 GB
Tool use
QW
Qwen2.5 Math 7B Instruct
Qwen · legraphista
Params7.62B
Context4K
Smallest1.9 GB
Tool use
AL
alpaca native i1
Alpaca · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
DE
Delphermes 8B
Delphermes · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use

Other quants

Keep browsing