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.
TI
TinyEnsemble-3x1.1B-TinyMoE
Tinyensemble · mradermacher
Params2.62B
Context4K
Q4_K_M1.6 GB
LL
llama-3-Nephilim-v2-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
PH
Phi 3 mini 4k instruct imatrix
Phi · duyntnet
Params3.82B
Context4K
Q4_K_M2.4 GB
LL
Llama 3.2 8X3B GATED MOE NEO Reasoning Dark Champion uncensored 18.4B IMAT
Llama · DavidAU
Params18.4B
Context128K
Q4_K_M11.3 GB
HA
Hathor v4.6 i1
Hathor · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GE
Gemma 4 Gembrain X 31B
Gemma · Nimbz
Params30.7B
Context256K
Q4_K_M18.7 GB
GR
Granite 20b Code Base
Granite · mradermacher
Params20B
Context8K
Q4_K_M12.8 GB
LL
Llama-3-Oasis-v1-OAS-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
MI
Magistral Small 2507 Rebased Vision
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CO
Cosmos Reason1 7B Heretic
Cosmos · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
LL
Meta Llama 3.1 8B Instruct
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
LL
OpenBioLLM Llama3 70B GGUF smashed
Llama · PrunaAI
Params70.6B
Context8K
Q4_K_M42.5 GB
LL
Llama 3 Youko 8b Instruct
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
LL
Llama 2 13b Hf
Llama · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
RW
rwkv 6 finch 1b6
Rwkv · latestissue
Params1.6B
Context1024K
Smallest0.7 GB
LL
Llama-3-Swallow-70B-v0.1
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
PY
Pythia 6.9b Deduped
Pythia · mradermacher
Params6.86B
Context2K
Q4_K_M4.4 GB
QW
Qwen3.5 9B Cyberpunk2077 Xiaotian All4 5pass
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
BA
BabyHercules 4x150M
Babyhercules · mradermacher
Params411M
Context2K
Q4_K_M0.3 GB
DE
Deepseek Llm 7b Chat Abliterated
DeepSeek · mradermacher
Params6.91B
Context4K
Q4_K_M4.2 GB
IN
Industry Coder 27B v1.0 BF16
Industry · kataguru
Params26.9B
Context256K
Q4_K_M2.0 GB
GO
Goetia 26B A4B v1.5
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
IG
Ignis 7B DPO Laser
Ignis · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
NE
Daredevil-8B-abliterated-dpomix
Neuraldaredevil · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
BO
Borealis Open 270m
Borealis · mradermacher
Params268M
Context32K
Q4_K_M0.3 GB
B3
B3 27B i1
mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
TR
Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B i1
Truthful · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
ST
State of the MoE RP 3x7b
State · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
DA
DarkForest 20B v2.0 Erebus Edition
Darkforest · mradermacher
Params20B
Context4K
Q4_K_M12.0 GB
AM
amalia-desenrasca-9b
Amalia · mradermacher
Params9.15B
Context32K
Q4_K_M5.6 GB