IQ2_S GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 26079 models have a IQ2_S file. Sizes run from 2M to 1030B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GL
GLM 5.3 Flash
GLM · AesSedai
Params321B
Context1024K
Q4_K_M202.0 GB
Vision
MI
Codestral 22B v0.1
Mistral · mradermacher
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
MA
MAmmoTH2-8B-Plus
Mammoth · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama2 7b chat uncensored i1
Llama · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
GA
GaMS3 12B Multimodal
Gams · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
HA
MN HaremUnion 12B i1
Haremunion · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GL
Glistening Gem 31B v2.1
Glistening · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
QW
Qwen3 8B 192k Josiefied Uncensored NEO Max
Qwen · DavidAU
Params8.19B
Context192K
Q4_K_M5.8 GB
ReasoningRoleplay
QW
Qwen3.5 27B Claude 4.6 OS Auto Variable Heretic Uncensored Thinking
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplay
MI
Ministral 3 8B Reasoning 2512 It
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool use
DE
Deita-34b
Deita · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
QW
Qwen3 Coder 42B A3B Instruct TOTAL RECALL MASTER CODER M 768k Ctx
Qwen · mradermacher
Params42.4B
Context768K
Q4_K_M25.7 GB
CodingReasoning
SA
Sailor2 20B Chat
Sailor · bartowski
Params19.2B
Context32K
Q4_K_M11.6 GB
GGUF
MI
Midnight Miqu 103B v1.0 i1
Midnight · mradermacher
Params103B
Context32K
Smallest22.0 GB
GGUF
TE
Tess 4 27B
Tess · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
ReasoningTool useVision
MI
Configurable-Mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DA
Dans PersonalityEngine V1.3.0 12b
Dans · bartowski
Params12.2B
Context128K
Q4_K_M7.5 GB
CodingRoleplay
BA
BanglaLLama-3-8b-BnWiki-Base
Banglallama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
MI
MiroThinker 1.7
Mirothinker · mradermacher
Params235B
Context256K
Q4_K_M142.2 GB
GGUF
NI
Ninja v1 NSFW 128k
Ninja · mmnga
Params7.24B
Context128K
Q4_K_M4.4 GB
GGUF
BI
Bigstral 12b 32k
Bigstral · mradermacher
Params12.5B
Context32K
Q4_K_M7.5 GB
GGUF
QW
Parable Qwen3 8B Claude Fable 5
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
AI
aixsatoshi Honyaku 13b
Aixsatoshi · mmnga
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
OL
Olmo 3 Think AIO
OLMo · prithivMLmods
Params32.2B
Context64K
Q4_K_M4.5 GB
Reasoning
BI
Bionic Cetacean 20B i1
Bionic · mradermacher
Params20B
Context4K
Q4_K_M12.0 GB
Roleplay
LL
nvidia Llama 3 3 Nemotron Super 49B v1 5
Llama · bartowski
Params49.9B
Context128K
Q4_K_M30.2 GB
GGUF
GR
granite 34b code instruct i1
Granite · mradermacher
Params33.7B
Context8K
Q4_K_M21.4 GB
CodingTool use
QW
Qwen1.5 MoE A2.7B Chat
Qwen · duyntnet
Params14.3B
Context32K
Q4_K_M9.5 GB
GGUF
HE
Hebrew_Nemo
Hebrew · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Base
DeepSeek · bartowski
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding

Other quants

Keep browsing