Q3_K_S GGUF models

3-bit k-quant, small. Small files with noticeable quality loss. 102724 models have a Q3_K_S file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
LI
Lilith 31B v1.0
Lilith · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
SO
SOLAR Platypus 10.7B v2
Solar · TheBloke
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
MI
Infinity Instruct 7M Gen Mistral 7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3.5 9B Abliterated
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
MI
models--automerger--T3qInex12-7B
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AU
Augmental ReMM 13B
Augmental · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
CH
Chaotic Order 24B V3
Chaotic · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
GP
gpt2
Gpt · QuantFactory
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
CH
chujiezheng Starling LM 7B beta ExPO
Chujiezheng · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 2507 4B Instruct Haiku 4.5 Merged
Qwen · bartowski
Params4B
Context256K
Q4_K_M2.6 GB
GGUF
IR
Irene-RP-v2-7B
Irene · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
QW
Qwen2 1.5B Instruct
Qwen · Goekdeniz-Guelmez
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
MI
MiniMax M3
Minimax · bartowski
Params426B
Context1024K
Q4_K_M261.3 GB
Vision
LL
Hermes 3 Llama 3.1 70B
Llama · legraphista
Params70.6B
Context128K
Smallest15.3 GB
RoleplayTool use
SE
Seed OSS 36B Instruct
Seed · bartowski
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
QW
Qwen3 0.6B Abliterated
Qwen · bartowski
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
AM
Amaretto 8B
Amaretto · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
Tool useVision
GE
Gemma 4 31B It SDFT Heretic RP
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Roleplay
LL
Llama-3-8B-Instruct-Gradient-1048k
Llama · crusoeai
Params8B
Context1024K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 30B A3B ArliAI RpR v4 Fast
Qwen · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
GGUF
SO
Solar Open 100B
Solar · mradermacher
Params103B
Context128K
Q4_K_M62.3 GB
GGUF
MI
uukuguy_speechless-code-mistral-7b-v1.0
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
MA
openaccess-ai-collective_manticore-13b
Manticore · TheBloke
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
RH
rho-math-1b-interpreter-v0.1
Rho · RichardErkhov
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
PI
maywell_pivot-sus-rp
Pivot · TheBloke
Params34.4B
Context8K
Q4_K_M20.7 GB
Roleplay
QW
Qwen2.5 1.5B Instruct
Qwen · QuantFactory
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
ZI
idea-ccnl_ziya-coding-34b-v1.0
Ziya · TheBloke
Params33.7B
Context16K
Q4_K_M20.2 GB
GGUF
DI
DialFactSum ACU 8B
Dialfactsum · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
WI
Wizard Vicuna 30B Uncensored
Wizard · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
QW
Qwen2 Audio 7B
Qwen · NexaAI
Params7.75B
Context8K
Q4_K_M4.8 GB
GGUF

Other quants

Keep browsing