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.
OL
Olmo 3 7B RL Zero IF
OLMo · mradermacher
Params7.3B
Context64K
Q4_K_M4.5 GB
SK
Skyfall 31B v4.1
Skyfall · mradermacher
Params31.4B
Context128K
Q4_K_M19.0 GB
LL
Polypsyche Llama 3.1 8B Instruct Agent 0.003 128K code ds auto Logic i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
HU
Huihui NeoHorse 1 4B Abliterated
Huihui · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
EX
Explore LM Ext 7B Math
Explore · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GE
Gemma 4 26B A4B StyleTune
Gemma · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
GE
Gemma 4 31B It Uncensored MAX
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
NO
Nova-1.2-0.8B
Nova · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
QW
Qwen2.5 7B Instruct
Qwen · duyntnet
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Qwen2.5 7B MegaScience
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
ST
Stellar Witch 12B
Stellar · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
FA
Fara 7B Abliterated v2
Fara · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
LL
Llama 3.2 3B Instruct Heretic Ablitered Uncensored
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
QW
LaSER Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
OM
Omega_Sapphira_Joyous L3.3 70B v1.1
Omega · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
OP
OpenThinkerAgent 32B
Openthinkeragent · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
WE
WebGen LM 32B
Webgen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
JI
JingSi V2 E4B
Jingsi · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
QW
PAPO G Qwen2.5 VL 7B
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
PH
Phi 3 medium 4k instruct imatrix
Phi · duyntnet
Params14B
Context4K
Q4_K_M8.6 GB
TR
Trinity Nano Base Pre Anneal
Trinity · mradermacher
Params6.12B
Context4K
Q4_K_M3.8 GB
LL
Llama3 OpenBioLLM 8B i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Bee1reason Arabic Qwen 14B
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
DR
Dream Coder v0 Base 7B
Dream · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Qwen2.5 8x7B Vee Eight Coder Instruct 53B 128k Ctx
Qwen · mradermacher
Params53.2B
Context128K
Q4_K_M32.4 GB
NE
OpenReasoning Nemotron 14B
Nemotron · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
QW
Qwen3.6 27B Abliterated rMAX
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
PL
PLLuM 12B Base 250801
Pllum · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
NE
Nemotron Cascade 14B Thinking
Nemotron · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
LL
Llamazing 3.1 8B Instruct i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB