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
QW
Qwen3 Esper3 Reasoning Instruct 6B Brainstorm20x Enhanced E32 128k Ctx
Qwen · mradermacher
Params5.94B
Context128K
Q4_K_M3.6 GB
CodingReasoning
CO
Codegeex4 All 9b
Codegeex · mradermacher
Params9.4B
Context128K
Q4_K_M6.3 GB
GGUF
VI
vicgalle Configurable Janus 7B
Vicgalle · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Dolphin3.0 R1 Mistral 24B
Mistral · eaddario
Params23.6B
Context32K
Q4_K_M13.1 GB
Reasoning
LL
Meta-Llama-3-8B-Instruct
Llama · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 14B Instruct Abliterated v2
Qwen · RichardErkhov
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
QW
Qwen3.8-27B
Qwen · SeraphicHero
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
MI
failspy Codestral 22B v0.1 abliterated v3
Mistral · RichardErkhov
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
MI
NSFW DPO Noromaid 7b Mistral 7B Instruct v0.1
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
Roleplay
PY
pythia-1.4b-dpo-full
Pythia · mradermacher
Params1.41B
Context2K
Q4_K_M0.9 GB
GGUF
QW
Samantha-qwen-0.5b-ptbr
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
LL
ADG CoT LLaMa3 8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
NO
North Mini Code 1.0
North · mradermacher
Params30.5B
Context488K
Q4_K_M18.6 GB
CodingReasoningTool use
NE
Neuron 46x4B
Neuron · mradermacher
Params125B
Context256K
Q4_K_M75.8 GB
Tool use
MA
Marconi v1 3x7B 10B MoE
Marconi · mradermacher
Params18.5B
Context32K
Q4_K_M11.2 GB
Tool use
FI
Fimbulvetr-11B-v2
Fimbulvetr · backyardai
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
LI
Lite Oute 1 300M Instruct
Lite · mradermacher
Params300M
Context4K
Q4_K_M0.2 GB
GGUF
NI
Nightshade-Violet-12B
Nightshade · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
QW
Qwen2.5 1.5B Instruct heretic
Qwen · saidutta69
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
MI
AmeerH Mistral Math 2x7b mix
Mistral · RichardErkhov
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
LL
Meta Llama Llama 3.2 3B Instruct Heretic Nosyco
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
GE
Gemma 2 27b It Abliterated
Gemma · RichardErkhov
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
AE
aegolius acadicus v1 30b i1
Aegolius · mradermacher
Params29.8B
Context32K
Q4_K_M18.0 GB
GGUF
CS
Csg Wukong 1B
Csg · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
QW
Qwen3 53B A3B 2507 THINKING TOTAL RECALL v2 MASTER CODER
Qwen · mradermacher
Params53B
Context256K
Q4_K_M32.1 GB
CodingReasoning
LL
TransLLaMA2-7B
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LU
Ko-Luxia-8B-it
Luxia · mradermacher
Params8.17B
Context8K
Q4_K_M5.0 GB
GGUF
AN
Andy 4.2
Andy · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use

Other quants

Keep browsing