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
Luau Devstral 24B Instruct v0.2
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding
SE
SenseNova U1.5 8B MoT
Sensenova · mradermacher
Params9.35B
Context256K
Q4_K_M5.7 GB
ReasoningTool use
VI
VisCoder 7B
Viscoder · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
LL
CodeLlama 13B Fireplace i1
Llama · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
CodingTool use
QW
Qwen3 0.6B Uncensored
Qwen · Null-Guard
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
PH
Phi 2 OmniMatrix
Phi · mradermacher
Params2.78B
Context2K
Q4_K_M1.7 GB
GGUF
DA
Daschund
Daschund · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
Tool use
LL
Llama 3.2 8X3B MOE Dark Champion Instruct Uncensored Abliterated 18.4B
Llama · mradermacher
Params18.4B
Context128K
Q4_K_M11.3 GB
GGUF
MI
Mistral Medium 3.5 128B Desiccated
Mistral · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
GGUF
FI
Fimburs11V3
Fimburs · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
SW
Swallow MS 7b v0.1
Swallow · mradermacher
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
GE
Gemma 4 12B It Guardpoint
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
Reasoning
UT
UtevoLux 3.6 27B
Utevolux · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
Qwen3.5 18b A3B Reap Coding Heretic v0
Qwen · mradermacher
Params18.5B
Context256K
Q4_K_M11.4 GB
GGUF
QW
Qwen3.5 9B Claude 4.6 OS HERETIC UNCENSORED INSTRUCT
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Roleplay
LI
Liquid A1B 8B PL Coder
Liquid · mradermacher
Params8.34B
Context125K
Q4_K_M5.0 GB
Coding
QW
Qwen2.5 14B Uncensored Instruct i1
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
LL
Fireball Alpaca Llama3.1.08 8B Philos C R1 i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
MI
Mistral Nemo Instruct 2407 abliterated
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GE
Gemma 2b It
Gemma · mradermacher
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
AT
Athnete 13B
Athnete · mradermacher
Params13B
Context4K
Q4_K_M8.1 GB
GGUF
QW
Qwen3.8 9B Heretic Uncensored
Qwen · marafx2007
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
LL
Llama3.1 MOE 4X8B Gated IQ Multi Tier Deep Reasoning 32B
Llama · mradermacher
Params24.9B
Context128K
Q4_K_M15.2 GB
ReasoningRoleplayTool use
GR
Granite 8b Code Instruct 128k
Granite · RichardErkhov
Params8.05B
Context125K
Q4_K_M4.9 GB
Coding
FA
Faithful_Thinking_with_Image
Faithful · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Reasoning
SW
Swallow-7b-hf
Swallow · mradermacher
Params6.83B
Context4K
Q4_K_M4.1 GB
GGUF
LI
LittleInstructionJudge 4B v0.1
Littleinstructionjudge · mradermacher
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
CH
Chocolatine 14B Instruct DPO v1.2
Chocolatine · mradermacher
Params14B
Context4K
Q4_K_M8.6 GB
GGUF
ER
Erk 32B
Erk · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
DI
DialoGPT MedDialog large
Dialogpt · mradermacher
Params838M
Context1K
Q4_K_M0.5 GB
GGUF

Other quants

Keep browsing