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
GR
GRM 3.2 Sky
Grm · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
MU
G4 26B A4B Musica v1
Musica · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplay
GO
Goetia 31B v1
Goetia · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
QW
Qwen3 0.6B
Qwen · NANI-Nithin
Params752M
Context40K
Q4_K_M0.5 GB
GGUF
SA
Saul Base Clown 7B Instruct slerp i1
Saul · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AP
Apex 2 Base
Apex · mradermacher
Params3.87B
Context4K
Q4_K_M2.4 GB
Coding
DE
L3.1 MOE 2X8B Deepseek DeepHermes e32 uncensored abliterated 13.7B i1
DeepSeek · mradermacher
Params13.7B
Context128K
Q4_K_M8.3 GB
ReasoningTool use
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · marafx2007
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
GR
Granite 3.0 8b Base
Granite · mradermacher
Params8.17B
Context4K
Q4_K_M4.9 GB
GGUF
VI
Viper Coder v1.6 R999
Viper · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
LL
Llama 3 portuguese Tom cat 8b instruct i1
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Ektome Qwen2.5 Coder 7B Instruct PristinelyUncensored
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
QwenStoryteller2
Qwen · mradermacher
Params7.6B
Context125K
Q4_K_M4.7 GB
ReasoningVision
GI
Ai Girlfriend v2
Girlfriend · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Ektome Qwen3 8B PristinelyUncensored
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
HE
G Health 32B Instruct
Health · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
LL
llama-joycaption-beta-one-hf-llava
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.0 GB
Tool useVision
QW
Qwen3.5 4B Abliterated Aggressive
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
HP
Hpc Coder v2 6.7b
Hpc · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
SmartSnap Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
LL
Llama 3.2 8X3B GATED MOE Reasoning Dark Champion Instruct Uncensored Abliterated 18.4B
Llama · mradermacher
Params18.4B
Context128K
Q4_K_M11.3 GB
ReasoningRoleplay
JA
AI21-Jamba-Reasoning-3B
Jamba · Mungert
Params3.2B
Context256K
Q4_K_M2.0 GB
ReasoningTool use
CA
Captain Eris Violet V0.420 12B i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
NE
Nebula 8lang 14b
Nebula · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingTool use
GL
GLM 4.7 Flash Absolute Heresy
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
DE
DeepSeek R1 Distill Llama 8B 3MPER0RR Abliterated
DeepSeek · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
GE
Gemma 4 E4B It Abliterated
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GGUF
AR
Artemis 31B v1.1
Artemis · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
QW
Qwen3 Embedding 8B
Qwen · mradermacher
Params7.57B
Context40K
Q4_K_M4.7 GB
Embedding
AN
Angelic_Eclipse_12B
Angelic · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF

Other quants

Keep browsing