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
SC
Schattenblume 31B
Schattenblume · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplay
KA
Karen_theEditor_13b_HF
Karen · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
GE
Gemma 4 Gembrain 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplay
LL
Llama 2 7b WikiChat
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
NA
NaNovel 9B
Nanovel · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
HU
HuatuoGPT 3 9B
Huatuogpt · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Reasoning
LL
Llama-3-Patronus-Lynx-70B-Instruct
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
QW
Qwopus3 5 9B Coder Flash
Qwopus · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
CodingReasoningTool use
QW
Qwen2.5 0.5B Instruct
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
LO
LogicLumina-L3-13B
Logiclumina · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
WA
Waifu Heretic 26b A4B
Waifu · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
SW
Swallow-70b-instruct-hf
Swallow · mradermacher
Params69.2B
Context4K
Q4_K_M41.5 GB
GGUF
LL
Herplete LLM Llama 3.1 8b i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Tool use
SM
SmolLlamix 8x101M take2
Smolllamix · mradermacher
Params399M
Context32K
Q4_K_M0.3 GB
GGUF
QW
Qwen3 The Josiefied Omega Directive 22B Uncensored Abliterated
Qwen · mradermacher
Params22B
Context40K
Q4_K_M13.3 GB
Roleplay
LO
MN LooseCannon 12B v2 i1
Loosecannon · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
LI
Ling 3.0 flash Sante Uncensored
Ling · AtomicChat
Params127B
Context256K
Smallest61.1 GB
ReasoningTool use
AI
Aitana 7B S Instruct
Aitana · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
QW
MiMo V2.6 Distill Qwen 9B Ablit
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Tool use
QW
Qwen3-8B-abliterated
Qwen · Mungert
Params8.2B
Context40K
Q4_K_M5.2 GB
GGUF
GP
Gpt2 Large
Gpt · mradermacher
Params838M
Context1K
Q4_K_M0.5 GB
GGUF
0X
0x01 8x7b hf i1
mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
AP
Apocrypha-7b
Apocrypha · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
LLaMA2-13B-Psyfighter2
Llama · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
LL
Llama3-8B-Instruct-Replete-Adapted
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
CodingTool use
GE
Gemma 4 31B It Abliterated
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
CH
Chaotic Harmony 24B
Chaotic · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
TE
TerminalHorizon 27B
Terminalhorizon · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
NE
Huihui NVIDIA Nemotron Nano 9B v2 Abliterated
Nemotron · mradermacher
Params8.89B
Context1024K
Q4_K_M6.5 GB
GGUF
NO
Nontoxic PiVoT Bagel RP 34b i1
Nontoxic · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
Roleplay

Other quants

Keep browsing