IQ3_S GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 45340 models have a IQ3_S file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
PY
Pythia 12b Deduped
Pythia · mradermacher
Params11.8B
Context2K
Q4_K_M7.6 GB
GGUF
MI
dolphin 2.8 mistral 7b v02
Mistral · bartowski
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
flammenai flammen20 mistral 7B
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
HA
Hathor_Respawn-L3-8B-v0.8
Hathor · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
OP
OpenChat 3.5 7B SOLAR v2.0 i1
Openchat · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
GE
Gemma 2 27b It
Gemma · mradermacher
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MI
Codestral-21B-Pruned
Mistral · mradermacher
Params21.5B
Context32K
Q4_K_M12.8 GB
Coding
MI
MiroThinker 1.7 Mini
Mirothinker · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
MI
MiniMax M3 Uncensored
Minimax · spiritfather
Params426B
Context1024K
Q4_K_M264.3 GB
GGUF
WE
WestLake 7B v2
Westlake · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
LL
Llama 3.2 Chibi 3B i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
RI
RigoChat 7b v2
Rigochat · IIC
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen3.6 40B Claude 4.6 Opus Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
CodingReasoningRoleplay
EU
Eurus 70b nca fixed
Eurus · mradermacher
Params69B
Context16K
Q4_K_M41.4 GB
Reasoning
PR
prodigy sm base v0.1
Prodigy · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GU
Gumini 1.5B Base i1
Gumini · GuminiResearch
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
MARTHA 73B Qwen2 VL i1
Qwen · mradermacher
Params72.7B
Context125K
Q4_K_M47.4 GB
Vision
OP
OpenELM-450M-Instruct
Openelm · RichardErkhov
Params457M
Context2K
Q4_K_M0.3 GB
GGUF
EU
EuroLLM 9B Instruct Heretic
Eurollm · mradermacher
Params9.15B
Context4K
Q4_K_M5.6 GB
Roleplay
QW
Huihui Qwen3 4B Instruct 2507 Abliterated
Qwen · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
NE
NeuralExperiment 7b MagicCoder v7
Neuralexperiment · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
MA
Magnum Picaro 0.7 v2 12b i1
Magnum · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
OX
OxytocinErosEngineeringF1 7B slerp
Oxytocinerosengineeringf · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
AS
Astrollama 3 8b Chat_Summary
Astrollama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3.5 27B Deckard PKD Heretic Uncensored Thinking
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplay
DA
L3 Dark Planet Horror City 8B NEO Imatrix
Dark · DavidAU
Params8B
Context8K
Q4_K_M4.9 GB
Roleplay
TU
Turbo Ai 7b
Turbo · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
GE
Gemma 4 E2B It GMCE
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool use
NE
Neuraltranslate 27b Mt Nah Es v1
Neuraltranslate · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
RE
Rei 12B V3 Base
Rei · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay

Other quants

Keep browsing