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
IC
IceEspressoRPv1 7b i1
Iceespressorpv · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 42B A3B Stranger Thoughts Deep20x Abliterated Uncensored
Qwen · mradermacher
Params42.4B
Context40K
Q4_K_M25.7 GB
ReasoningRoleplay
SO
SOCAM V1
Socam · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
LF
LFM2.5 2.6B Tema_Q Abliterated
Lfm · mradermacher
Params2.7B
Context128K
Q4_K_M1.7 GB
GGUF
DE
deepseek llm 67b chat i1
DeepSeek · mradermacher
Params67.4B
Context4K
Q4_K_M40.4 GB
GGUF
WE
WestLakev2 IreneRP Neural 7B slerp
Westlakev · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
GE
Gemma 4 12B Uncensored Opus4.7 Cot
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
QW
Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
LL
Llama 3.3 70B Instruct Heretic
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
WI
WizardCoder Python 13B V1.0
Wizardcoder · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
Coding
DE
deepseek-coder-1.3b-instruct
DeepSeek · duyntnet
Params1.35B
Context16K
Q4_K_M0.9 GB
Coding
QR
Qra 13B chat i1
Qra · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
FI
Fimbulvetr 11B v2 iMat
Fimbulvetr · InferenceIllusionist
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
LI
Liberated Miqu 70B i1
Liberated · mradermacher
Params69B
Context32K
Q4_K_M41.7 GB
GGUF
CH
Chocolatine 14B Instruct DPO v1.1 i1
Chocolatine · mradermacher
Params14B
Context4K
Q4_K_M8.6 GB
GGUF
TI
TinySolar-248m-4k-py
Tinysolar · RichardErkhov
Params248M
Context32K
Q4_K_M0.2 GB
GGUF
IR
IreneRP Neural 7B slerp
Irenerp · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
Roleplay
YI
Yi-1.5-9B
Yi · mradermacher
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
KA
KangalKhan RawRuby 7B
Kangalkhan · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3.8 27B Uncensored FP8
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
Qwen3.8 27B Continuum
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplay
QW
Qwen3.6 Fallen Fabulist 35B A3B Heretic
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
Roleplay
QW
Qwen3 Esper3 Reasoning Instruct 6B Brainstorm20x Enhanced E32
Qwen · mradermacher
Params5.94B
Context40K
Q4_K_M3.6 GB
CodingReasoning
MY
MythoMax L2 13b
Mythomax · mradermacher
Params13B
Context4K
Q4_K_M8.1 GB
GGUF
LL
Llama3-18B-lingyang-v1
Llama · mradermacher
Params18.1B
Context1024K
Q4_K_M10.9 GB
GGUF
GE
Gemma 4 26B A4B Heretic Stable
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Reasoning
OP
OpenResearcher 30B A3B
Openresearcher · mradermacher
Params31.6B
Context1024K
Q4_K_M24.5 GB
GGUF
LL
Configurable Llama 3.1 8B Instruct i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
CO
ConfigurableBeagle-11B
Configurablebeagle · RichardErkhov
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
QW
Qwen3 30B A1.5B 64K High Speed NEO Imatrix MAX
Qwen · DavidAU
Params30.5B
Context64K
Q4_K_M18.6 GB
ReasoningRoleplayTool use

Other quants

Keep browsing