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.
QW
Qwen3.8 27B ScientificBM
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
LL
Llama 2 7b Ultrachat
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
MI
Mixnu i1
Mixnu · mradermacher
Params19.8B
Context4K
Q4_K_M12.0 GB
MP
Mpt 30b Chat
Mpt · mradermacher
Params30B
Context8K
Q4_K_M19.1 GB
MI
Mixtral AI CyberLord
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.5 9B Theseus
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
QW
Qwen3.5 27B Writer V2
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
NO
Notus-TheTop-7b-Passthrough
Notus · mradermacher
Params8.99B
Context32K
Q4_K_M5.4 GB
GO
Godoter3.8 27B
Godoter · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
QW
LightGPT 7B Qwen2
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
XO
XortronCriminalComputingConfig
Xortroncriminalcomputingconfig · darkc0de
Params23.6B
Context32K
Q4_K_M14.3 GB
PL
G4 Plainsong 12B
Plainsong · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
LL
Higgs-Llama-3-70B
Llama · legraphista
Params70.6B
Context8K
Smallest15.3 GB
BA
bagel 7b v0.5
Bagel · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
MA
Marco DeepResearch 8B
Marco · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
RO
roleplay mis wes
Roleplay · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
AE
aegolius acadicus 24b v2 i1
Aegolius · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
LL
Llama3 8b Cpt Sealionv2 Base
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
RE
REBEL-OpenChat-3.5
Rebel · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
BO
Boundary Solar Chat 2x10.7B MoE
Boundary · mradermacher
Params19.2B
Context4K
Q4_K_M11.6 GB
AD
Adamus-7B-slerp
Adamus · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.6 35B A3B Heretic v2
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
LL
picAIso TARS 8B llama REMIX v2
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
PA
PandafishHeatherReReloaded
Pandafishheatherrereloaded · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Llama-3-Instruct-8B-SPPO-Iter3
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
TR
Translategemma 12b It
Translategemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
CH
Chocolatine 14B Instruct 4k DPO
Chocolatine · mradermacher
Params14B
Context4K
Q4_K_M8.6 GB
DE
DeepSeek V2 Lite Chat
DeepSeek · duyntnet
Params15.7B
Context160K
Q4_K_M10.4 GB
GR
Granite 7b Base
Granite · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
CO
CodeV-DS-6.7B
Codev · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB