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
Qwen2.5 14B
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
Roleplay
DI
dictalm2.0-instruct
Dictalm · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
QW
VulnLLM-R-7B
Qwen · Mungert
Params7.6B
Context32K
Q4_K_M4.9 GB
CodingReasoning
AQ
Aquif Grounding 7B
Aquif · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
CO
codegemma-2b
Codegemma · bartowski
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
UG
L3-8B-UGI-DontPlanToEnd-test
Ugi · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 7B Instruct 1M Thinking Claude Gemini GPT5.2 DISTILL PaperWitch Heresy
Qwen · mradermacher
Params7.62B
Context986K
Q4_K_M4.7 GB
ReasoningRoleplay
QW
Qwen2.5 8x7B Vee Eight Coder Instruct 53B
Qwen · mradermacher
Params53.2B
Context32K
Q4_K_M32.4 GB
CodingTool use
KR
KrakenSakura Maelstrom 12B v1
Krakensakura · Naphula
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
TI
TinySlime-1.1B-Chat-v1.0
Tinyslime · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
MO
MotherEarth_1.0
Motherearth · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Roleplay
LL
Fireball Llama 3.1 8B Philos Reflection v0.3 i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen3.6 27B A3B Coder
Qwen · mradermacher
Params26.2B
Context256K
Q4_K_M16.1 GB
Coding
LF
LFM2.5 1.2B Instruct heretic
Lfm · saidutta69
Params1.17B
Context125K
Q4_K_M0.7 GB
ReasoningRoleplayTool use
QW
Qwen3 VL 12B Thinking Brainstorm20x
Qwen · mradermacher
Params11.9B
Context256K
Q4_K_M7.2 GB
CodingReasoningVision
SA
Sarashina2.2 1b Instruct v0.1
Sarashina · mmnga
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
CA
Calme-7B-Instruct-v0.1.1
Calme · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
AR
ARK 270M Base i1
Ark · usermma
Params252M
Context2K
Q4_K_M0.2 GB
GGUF
GE
Gemma-4-26B-A4B-It-Ultra-Uncensored-Heretic
Gemma · JMingo
Params25.2B
Context256K
Q4_K_M16.9 GB
GGUF
QW
Qwen2.5 Godzilla Coder V2 51B
Qwen · mradermacher
Params51B
Context32K
Q4_K_M30.7 GB
Coding
QW
Qwen3 Coder Next REAP 40B A3B
Qwen · mradermacher
Params41B
Context256K
Q4_K_M25.0 GB
Coding
MI
Sydney_Pirate_Mistral_7b
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
Menage 12B
Menage · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
LO
LogicLumina-L3-13B-v2
Logiclumina · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
LL
Citrus1.0 Llama 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
QW
UD 2.0 Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled
Qwen · mfielding92
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningVision
KH
kheops compressed
Kheops · mradermacher
Params283M
Context2K
Q4_K_M0.2 GB
GGUF
EU
Eurus 70b sft fixed
Eurus · mradermacher
Params69B
Context16K
Q4_K_M41.4 GB
Reasoning
PE
Peach 2.0 9B 8k Roleplay Heretic
Peach · mradermacher
Params8.83B
Context16K
Q4_K_M5.3 GB
Roleplay
CH
Chewy-Lemon-Cookie-11B
Chewy · mradermacher
Params10.7B
Context8K
Q4_K_M6.5 GB
Roleplay

Other quants

Keep browsing