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
LL
Llama 3.1 SuperNova Lite
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
GGUF
PE
PersianMind v1.0
Persianmind · RichardErkhov
Params6.8B
Context2K
Q4_K_M4.1 GB
GGUF
AY
aya-23-35B
Aya · legraphista
Params35B
Context8K
Smallest8.5 GB
GGUF
GR
grimjim kunoichi lemon royale 7B
Grimjim · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
AU
AutoCoder
Autocoder · legraphista
Params33.3B
Context16K
Smallest7.2 GB
Coding
QW
Qwen3.6 35B A3B
Qwen · eaddario
Params34.7B
Context—
Smallest0.4 GB
GGUF
MO
MOSS Image Base
Moss · leejet
Params5.08B
Context—
Smallest2.2 GB
GGUF
UM
Umbra-v3-MoE-4x11b-2ex
Umbra · RichardErkhov
Params36.1B
Context32K
Q4_K_M21.8 GB
GGUF
DA
Dart Math Dsmath 7b Prop2Diff
Dart · RichardErkhov
Params6.89B
Context4K
Q4_K_M4.2 GB
GGUF
JS
jsfs11 MixtureofMerges MoE 2x7bRP v8
Jsfs · RichardErkhov
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
QW
Qwen3.5 35B A3B
Qwen · titan0115
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
GR
granite-7b-base
Granite · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
SH
Shieldgemma 27b
Shieldgemma · legraphista
Params27.2B
Context8K
Smallest6.1 GB
GGUF
LL
Llama3 8b It Translation Sharegpt En Ko
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
DA
datagemma rag 27b it IMat
Datagemma · legraphista
Params27.2B
Context8K
Smallest6.1 GB
GGUF
MI
grimjim Mistral Starling merge trial3 7B
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
FA
Falcon H1 1.5B Deep Instruct
Falcon · tiiuae
Params1.55B
Context128K
Q4_K_M0.9 GB
GGUF
MO
MOSS Image
Moss · PALLER-NOVUS
Params5.08B
Context—
Smallest1.2 GB
GGUF
QW
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · longsesh
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
LL
hf 100 Llama 3.1 Spellbound StoryWriter 0.1 vllm 16bit
Llama · RichardErkhov
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
WH
whisper medium
Whisper · oxide-lab
Params764M
Context—
Smallest0.3 GB
GGUF
YI
Yi-9B-Coder
Yi · legraphista
Params8.83B
Context4K
Smallest2.0 GB
Coding
PH
Phi 3 mini 4k instruct IMat
Phi · legraphista
Params3.82B
Context4K
Smallest0.8 GB
GGUF
SM
SmallThinker 4BA0.6B Instruct
Smallthinker · Tiiny
Params4.27B
Context32K
Smallest1.9 GB
GGUF
CH
Chunky-Lemon-Cookie-11B
Chunky · RichardErkhov
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · RichardErkhov
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
QW
Qwen Image 2.1 Turbo Uncensored
Qwen · suryatmodulus
Params8.19B
Context256K
Smallest3.3 GB
CodingTool useVision
SZ
szymonrucinski Curie 7B v1
Szymonrucinski · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
EV
Evolutionstory
Evolutionstory · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TI
Tinystories Lay8 Hs512 Hd8 33M
Tinystories · RichardErkhov
Params165M
Context512
Q4_K_M0.1 GB
GGUF

Other quants

Keep browsing