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
MI
MiniCPM V 2 6
MiniCPM · openbmb
Params7.61B
Context32K
Q4_K_M4.7 GB
Vision
QW
Qwen3.8 27B Uncensored Heretic Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
LL
Dolphin 3.0 Llama 3.2 3B
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingTool use
LL
Meta llama_Meta Llama 3 70B Instruct
Llama · ThomasBaruzier
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
DE
DeepSeek Coder V2 Lite Instruct Abliterated
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
LY
Lythri 4B A2B
Lythri · mradermacher
Params4.63B
Context128K
Q4_K_M3.4 GB
GGUF
GL
Huihui GLM 4.7 Flash Abliterated
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
TA
UI TARS 1.5 7B
Tars · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
FL
FLUX.2 klein base 4B
Flux · unsloth
Params3.88B
Context—
Q4_K_M2.4 GB
GGUF
GR
Granite 4.1 8b
Granite · ibm-granite
Params8.79B
Context128K
Q4_K_M5.3 GB
GGUF
QW
Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
Qwen2.5 Coder 3B Instruct Abliterated
Qwen · bartowski
Params3.09B
Context32K
Q4_K_M1.9 GB
Coding
GP
OpenAI Gpt Oss 20B Claude 4.5 Opus Heretic Uncensored
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Reasoning
AR
Artemis 31B v1.2 Abliterix v2
Artemis · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
LL
Llama-4-Maverick-17B-128E-Instruct
Llama · unsloth
Params400B
Context1024K
Q4_K_M242.8 GB
Vision
GE
Gemma The Writer N Restless Quill 10B
Gemma · DavidAU
Params10B
Context8K
Q4_K_M6.1 GB
Roleplay
MU
Music Flamingo Hf
Music · mradermacher
Params7.61B
Context32K
Q4_K_M4.7 GB
ReasoningVision
MI
MiniCPM V 4.7 35B A3B
MiniCPM · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
KI
Kimi-K2.5
Kimi · unsloth
Params1030B
Context256K
Q4_K_M621.2 GB
GGUF
QW
Qwen3-30B-A3B-Thinking-2507
Qwen · unsloth
Params30.5B
Context256K
Q4_K_M18.6 GB
Reasoning
QW
Qwen3.5-0.8B
Qwen · unsloth
Params773M
Context256K
Q4_K_M0.5 GB
Vision
QW
Qwen3.8-27B
Qwen · 6block
Params27B
Context256K
Q4_K_M17.7 GB
Vision
DE
Deepseek-V3.1
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M405.4 GB
GGUF
LL
Nidum Llama 3.2 3B Uncensored
Llama · lemuralabs
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingRoleplay
QW
Qwen3.6 35B A3B Anko
Qwen · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision
NA
Nanonets-Ocr-S
Nanonets · unsloth
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
VE
UI Venus 2 9B
Venus · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Vision
LT
LTX2.3 10Eros 1.5
Ltx · vantagewithai
Params21B
Context—
Q4_K_M14.3 GB
GGUF
AR
Artemis 31B v1.2
Artemis · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
MU
Murasaki 4B v0.3
Murasaki · mradermacher
Params4.41B
Context32K
Q4_K_M2.7 GB
GGUF

Other quants

Keep browsing