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.
NO
NousCoder 14B
Nouscoder · mradermacher
Params14.8B
Context80K
Q4_K_M9.0 GB
LO
Love Aligned 31B
Love · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
QW
Huihui Qwen3.6 35B A3B Claude 4.6 Opus Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
PR
PrincipiaMistralModel7B
Principiamistralmodel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen2.5 GenX 14B
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
QW
Qwen2.5-VL-32B-Instruct
Qwen · Mungert
Params32.8B
Context125K
Q4_K_M20.1 GB
LL
Llama 3 Tulu v2.5 8b Uf Mean 70b Uf Rm
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
QW
Qwen3 4B Instruct 2507 20250808 233922 0
Qwen · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
QW
Qwen3.5 9b Nsfw Captioning v5
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
DE
DeepSeek R1 Distill Llama 70B Heretic
DeepSeek · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
QW
Qwen3 VL 30B A3B Thinking Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
TA
C1 Tachu
Tachu · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
FA
Fara 7B
Fara · prithivMLmods
Params7.62B
Context125K
Q4_K_M4.7 GB
BL
Blossom v3 Baichuan2 7b
Blossom · mradermacher
Params7.51B
Context4K
Q4_K_M4.6 GB
HU
HuatuoGPT O1 8B
Huatuogpt · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
PO
Poro 34B i1
Poro · mradermacher
Params35.1B
Context7K
Q4_K_M22.4 GB
QW
Qwen3 Esper3 Reasoning CODER Instruct 12B Brainstorm20x 128k Ctx
Qwen · mradermacher
Params11.9B
Context128K
Q4_K_M7.2 GB
BE
4BeastsOfApocalypse
Beastsofapocalypse · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
HU
Huihui IQuest Coder V1 40B Instruct Abliterated
Huihui · mradermacher
Params39.8B
Context128K
Q4_K_M24.0 GB
NO
Nova 24b Cybersec
Nova · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
MI
Mistral 7B Instruct RR Abliterated
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
KO
Koala 13B HF
Koala · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
QW
Qwen3 Swallow 30B A3B RL v0.2 Heretic
Qwen · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
MO
mox 8b i1
Mox · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
AS
DarkArtsForge__Asmodeus 24B v2
Asmodeus · Naphula-Archives
Params23.6B
Context128K
Q4_K_M14.3 GB
QW
Qwen 3 14B Gemini v0.1
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
QW
Qwen2.5 Coder 32B YOYO
Qwen · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
GL
LFM2 8B A1B GLM 4.7 Flash Thinking Quantum IQ1C P
GLM · mradermacher
Params8.34B
Context125K
Q4_K_M5.0 GB
RI
Ring Mini 2.0
Ring · mradermacher
Params16.3B
Context32K
Q4_K_M9.9 GB
QW
Qwen3.5 4B Instruct SingleTurn
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB