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.
QW
Qwen3.5 Uncensored Aggressive
Qwen · tripolskypetr
Params122B
Context256K
Q4_K_M1.3 GB
SP
speakleash Bielik 7B Instruct v0.1
Speakleash · RichardErkhov
Params7.24B
Context4K
Q4_K_M4.4 GB
QW
Qwen2.5 3B Instruct
Qwen · legraphista
Params3.09B
Context32K
Smallest0.8 GB
PH
Phi 3 medium 4k instruct IMat
Phi · legraphista
Params14B
Context4K
Smallest3.0 GB
LL
colossal llama 2 7b base
Llama · shaowenchen
Params7.04B
Context4K
Smallest3.0 GB
IS
Isaak Carter J.O.S.I.E.3 Beta9 7B slerp
Isaak · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
QW
xpo-qwen2
Qwen · RichardErkhov
Params494M
Context32K
Q4_K_M0.4 GB
MI
Minitron 8B Base
Minitron · legraphista
Params8.27B
Context4K
Smallest3.6 GB
LL
tifa benchmark llama2 tifa question generation
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
LL
grimjim Llama 3 Instruct demi merge 8B
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
MV
mvpmaster NeuralDareDMistralPro 7b slerp
Mvpmaster · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
aifeifei798 DarkIdol Llama 3.1 8B Instruct 1.0 Uncensored
Llama · RichardErkhov
Params8B
Context—
Q4_K_M0.0 GB
QW
gte-Qwen2-7B-instruct
Qwen · RichardErkhov
Params7.61B
Context128K
Q4_K_M4.7 GB
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · anonymous12122
Params7.52B
Context128K
Q4_K_M5.3 GB
PH
chrisob94 phi 3 7b dissertation doc chat experiment 10 fold
Phi · RichardErkhov
Params3.82B
Context4K
Q4_K_M2.3 GB
FL
flux 3 image klein base
Flux · leejet
Params5.54B
Context—
Smallest2.3 GB
LL
Llama-3-8B-Instruct-64k
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
QW
Qwen2.5 7B Instruct
Qwen · legraphista
Params7.62B
Context32K
Smallest1.9 GB
XL
xLAM 7b R
Xlam · legraphista
Params7.24B
Context32K
Smallest1.6 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
JP
jpacifico Chocolatine 14B Instruct 4k DPO
Jpacifico · RichardErkhov
Params14B
Context4K
Q4_K_M8.6 GB
QW
Qwen2.5 72B Instruct
Qwen · legraphista
Params72.7B
Context32K
Smallest23.7 GB
SP
Spark X2.5 4B
Spark · eaddario
Params4.11B
Context—
Smallest0.0 GB
ST
L3-8B-Stheno-v3.2
Stheno · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
NE
addis scribe streaming
Nemotron · addisai
Params99M
Context—
Smallest0.0 GB
LL
Llama 3.1 Minitron 4B Width Base
Llama · legraphista
Params4.51B
Context128K
Smallest1.8 GB
MA
Matter 0.1 7B Boost
Matter · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
AR
arcee ai Saul Instruct Clown 7b
Arcee · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP
Qwen · Warumauchimmer
Params1.86B
Context—
Smallest0.9 GB