Q3_K GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 15171 models have a Q3_K file. Sizes run from 1M to 5632B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · xrachelburns
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
QW
Qwen3.8-27B
Qwen · Shishkipiski
Params27.3B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
YI
01 ai Yi 6B 200K
Yi · RichardErkhov
Params6.06B
Context195K
Q4_K_M3.7 GB
GGUF
QW
Qwen3.8-27B
Qwen · yachiyo8080
Params27.3B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
LL
Llama 3.2 3B Instruct
Llama · legraphista
Params3.21B
Context128K
Smallest0.9 GB
GGUF
OR
Ornith 1.5 122B DFlash2
Ornith · kaivoss
Params930M
Context256K
Q4_K_M0.6 GB
GGUF
QW
Qwenmodel1st
Qwen · atypical-chai
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
QW
Qwen3.8-27B
Qwen · Kaktus4048
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
XL
xLAM 8x22b R
Xlam · legraphista
Params141B
Context64K
Smallest29.7 GB
Tool use
K2
K2-ckpt_360
legraphista
Params65B
Context2K
Smallest14.2 GB
GGUF
QW
Qwen3.8-27B
Qwen · rax4901
Params27.3B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
CO
C4Ai Command R Plus 08 2024
Command R · legraphista
Params104B
Context128K
Smallest23.2 GB
GGUF
GR
Granite 20b Code Instruct R1.1
Granite · RichardErkhov
Params20B
Context8K
Q4_K_M12.8 GB
CodingReasoning
QW
Qwen3.8-27B
Qwen · loscrossos
Params27.3B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
QW
Qwen2-0.5B
Qwen · legraphista
Params494M
Context128K
Smallest0.3 GB
GGUF
QW
qwen3 asr 0.6b
Qwen · cstr
Params938M
Context—
Smallest0.0 GB
GGUF
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · kamjin
Params7.5B
Context128K
Q4_K_M5.3 GB
Vision
QW
Qwen3.8-27B
Qwen · LxBarn
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
LL
Meta-Llama-3-8B-Instruct-abliterated-v3
Llama · legraphista
Params8B
Context8K
Smallest2.0 GB
GGUF
RE
Realistic Vision V6.0 B1
Realistic · second-state
Params1.07B
Context—
Smallest1.5 GB
GGUF
GR
Granite 34b Code Instruct 8k
Granite · RichardErkhov
Params33.7B
Context8K
Q4_K_M21.4 GB
Coding
LL
dolphin-2.9.1-llama-3-8b
Llama · legraphista
Params8B
Context8K
Smallest2.0 GB
CodingTool use
WH
whisper large v3 turbo
Whisper · oxide-lab
Params809M
Context—
Smallest0.3 GB
GGUF
CO
codegeex4-all-9b
Codegeex · legraphista
Params9.4B
Context128K
Smallest3.1 GB
GGUF
GE
Vikhr-Gemma-2B-instruct
Gemma · Vikhrmodels
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
FL
FLUX.1 dev
Flux · leejet
Params11.9B
Context—
Smallest4.2 GB
GGUF
YI
Yi 1.5 34B
Yi · RichardErkhov
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
GR
Granite 20b Functioncalling
Granite · RichardErkhov
Params20B
Context8K
Q4_K_M12.8 GB
GGUF
GR
Granite 20b Code Base R1.1
Granite · RichardErkhov
Params20B
Context8K
Q4_K_M12.8 GB
CodingReasoning
QW
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · Unrestricted
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision

Other quants

Keep browsing