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
MI
Mistral 7B Instruct v0.2
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OP
OpenELM-1_1B-Instruct
Openelm · RichardErkhov
Params1.08B
Context2K
Q4_K_M0.7 GB
GGUF
UN
UNA POLAR 10.7B InstructMath v2 i1
Una · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
QW
Qwen2-57B-A14B-Instruct
Qwen · legraphista
Params57.4B
Context32K
Smallest21.1 GB
GGUF
QW
Qwen3 Sex
Qwen · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool use
GE
Aidc 5k Laos Gemma 3 4b It v2
Gemma · mradermacher
Params4.55B
Context128K
Q4_K_M2.9 GB
GGUF
EV
EAN 3B i1
Evan · mradermacher
Params3.4B
Context125K
Q4_K_M2.1 GB
Reasoning
QW
Qwen2.5 Coder 7B
Qwen · duyntnet
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
LL
Code-Llama-Bagel-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Coding
SC
Scout 8b
Scout · mradermacher
Params8.31B
Context32K
Q4_K_M5.1 GB
ReasoningRoleplay
YI
EVA Yi 1.5 9B 32K V1
Yi · mradermacher
Params8.83B
Context32K
Q4_K_M5.3 GB
GGUF
MY
L3-15B-MythicalMaid-t0.0001
Mythicalmaid · mradermacher
Params15B
Context8K
Q4_K_M9.1 GB
GGUF
DA
danube2-1.8b-openhermes
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
Tool use
QW
Qwen3-30B-A3B-Instruct-2507
Qwen · byteshape
Params30.5B
Context256K
Smallest10.2 GB
GGUF
VI
VibeWorlder 30B A3B
Vibeworlder · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
NE
nexus coder
Nexus · King3Djbl
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
DE
Qwen3.5 9B DeepSeek V4 Flash
DeepSeek · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwen3 Next 80B A3B Thinking GRPO Uncensored
Qwen · mradermacher
Params80B
Context256K
Q4_K_M48.5 GB
Reasoning
SA
Salt Asr_Wav Uni_1_Tts_Wav Uni_1 12k
Salt · RichardErkhov
Params3.23B
Context128K
Q4_K_M2.0 GB
GGUF
EE
EEVE-Korean-10.8B-instruct-v4-sft
Eeve · mradermacher
Params10.8B
Context4K
Q4_K_M6.5 GB
GGUF
IO
IoGPT A1 Instruct i1
Iogpt · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
MI
Mahou-1.2a-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
HE
Hemmingway 1
Hemmingway · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
Qwen3 06B 3MPER0RR Abliterated
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
SC
Scout 4b
Scout · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningRoleplay
QW
Qwen3 42B A3B 2507 TOTAL RECALL v2 Medium MASTER CODER
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoning
LL
Llama-3-70B-Synthia-v3.5
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
QW
Qwen3.5 4B Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
LI
Ling 3.0 Tiny Uncensored Abliterated
Ling · mradermacher
Params7.89B
Context128K
Q4_K_M4.8 GB
Reasoning
VE
Veena
Veena · Mungert
Params3.78B
Context128K
Q4_K_M2.5 GB
GGUF

Other quants

Keep browsing