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
QW
LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2
Qwen · mradermacher
Params8.34B
Context125K
Q4_K_M5.0 GB
GGUF
HA
Harbinger 24B
Harbinger · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
DE
Llama 3 DeepSeek R1 Distill 8B LewdPlay Uncensored i1
DeepSeek · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Reasoning
GE
C2S-Scale-Gemma-2-27B
Gemma · Mungert
Params27.2B
Context8K
Q4_K_M16.7 GB
GGUF
BL
Q3.5 BlueStar v2 27B Ultra Uncensored Heretic v2
Bluestar · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplayTool use
QW
Qwen2.5 14B Instruct Darija
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
UM
AQUILA Engine v1 i1
Uma · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
LL
Meta-Llama-3-8B-Instruct
Llama · duyntnet
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
EV
Evertide RX 12B
Evertide · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
LL
Llama PLLuM 70B Instruct 2512
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
QW
Qwen3 VL 30B A3B Instruct Abliterated v1
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
QW
Qwen3 VL 32B Thinking Abliterated v1
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
ReasoningTool useVision
QW
Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x
Qwen · mradermacher
Params21B
Context40K
Q4_K_M12.8 GB
CodingReasoning
LL
Llama 3 Tulu v2.5 8b Uf Mean 70b Uf Rm Mixed Prompts
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
MI
SlimHercules-4.0-Mistral-7B-v0.2
Mistral · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 30B A3B YOYO V2 GLM 4.7 Flash Instruct
Qwen · mradermacher
Params30.5B
Context986K
Q4_K_M18.6 GB
ReasoningTool use
XO
XORTRON CriminalComputing EnablementEngine v0.3
Xortron · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
LU
LucidVitality 9b
Lucidvitality · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
XO
XORTRON.CriminalComputing.Config.LARGE.XPRT2
Xortron · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
GGUF
AI
Airoboros L2 7b Gpt4 M2.0
Airoboros · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MA
Marco Mini Global Base
Marco · mradermacher
Params17.4B
Context32K
Q4_K_M10.6 GB
GGUF
QW
Qwen2.5 Wolverine CODER 11B
Qwen · mradermacher
Params10.9B
Context32K
Q4_K_M6.6 GB
Coding
QW
UnifiedReward 2.0 Qwen 7b
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QA
QAZTECH Azure Engineer 8B
Qaztech · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
QW
Qwen3.6-35B-A3B
Qwen · sphaela
Params35.5B
Context256K
Q4_K_M21.7 GB
Vision
YI
Yi 34B i1
Yi · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
QW
Qwen3.8 27B Dominatrix
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
TR
Triangulum 10B It
Triangulum · mradermacher
Params10.3B
Context32K
Q4_K_M6.3 GB
Reasoning
LL
DarkIdol Llama 3.1 8B Instruct 1.3 Uncensored
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
QW
Qwen3.5 122B A10B
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
GGUF

Other quants

Keep browsing