Tiny GGUF models

62726 GGUF models with 3B parameters or fewer. Sizes run from 1M to 3.5B parameters. The longest trained context is 795898K tokens.

Most downloadedNewestLargestLongest contextSmallest
BA
BabyMistral
Babymistral · mradermacher
Params1.55B
Context8K
Q4_K_M0.9 GB
GGUF
GE
gemma 4 12B it qat assistant MTP Q8 0
Gemma · Janvitos
Params423M
Context256K
Smallest0.5 GB
GGUF
QW
Qwen3-ASR-0.6B
Qwen · OpenVoiceOS
Params938M
Context—
Smallest1.9 GB
GGUF
BI
bitvla libero
Bitvla · vrfai
Params1.03B
Context—
Smallest1.4 GB
GGUF
CO
Yi Coder 1.5B Chat
Coder · QuantFactory
Params1.48B
Context128K
Q4_K_M1.0 GB
Coding
MU
Muse-Glimmer-30B-DFlash2
Muse · incoai
Params2.77B
Context128K
Q4_K_M1.6 GB
GGUF
WA
Wan2.1 T2V 1.3B
Wan · off-grid-ai
Params1.42B
Context—
Smallest0.8 GB
GGUF
QW
Qwen3.8 Distilled 2B NPU2
Qwen · Atomic-Germ
Params1.88B
Context256K
Smallest2.0 GB
ReasoningVision
SO
Soprano 1.1 80M
Soprano · BricksDisplay
Params30M
Context—
Q4_K_M0.0 GB
GGUF
QW
Qwen3.8 2B Heretic Max
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
OU
outetts 0.3 1b
Outetts · cstr
Params1.19B
Context—
Smallest0.1 GB
GGUF
QW
Qwen2.5 1.5B VibeThinker Heretic Uncensored Abliterated
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
GGUF
OP
OpenELM 1_1B Fix Nan
Openelm · mradermacher
Params1.08B
Context2K
Q4_K_M0.7 GB
GGUF
MI
MiniCPM5 2B
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingTool use
LL
FineMath Llama 3B
Llama · bartowski
Params3.21B
Context4K
Q4_K_M2.0 GB
GGUF
MI
MiniCPM V 4.7 35B A3B DSpark
MiniCPM · UserSuxx
Params389M
Context256K
Q4_K_M0.2 GB
Vision
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
CodingTool use
LF
lfm2.5 2.6b fable5 coding agent heretic
Lfm · AzariazIZI
Params2.7B
Context128K
Q4_K_M1.7 GB
Tool use
MA
Mamba 790m Hf
Mamba · mradermacher
Params790M
Context1024K
Q4_K_M0.5 GB
GGUF
CO
confucius4 r2t2
Confucius · cstr
Params2.35B
Context—
Smallest1.5 GB
GGUF
MI
MiniCPM5 2B Abliterated
MiniCPM · SC117
Params2.52B
Context128K
Q4_K_M1.6 GB
GGUF
LL
DOLPHIN3.0 L3.2 1B RP UNCENSORED
Llama · Novaciano
Params1.24B
Context128K
Smallest0.7 GB
CodingRoleplayTool use
SU
suna v1
Suna · jjcoders
Params190M
Context—
Q4_K_M0.4 GB
GGUF
QW
Qwen2.5 VL 3B Instruct Unredacted MAX
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
MI
MiniCPM5 1B
MiniCPM · mradermacher
Params1.08B
Context128K
Q4_K_M0.7 GB
Tool use
SA
Sarashina2.2 0.5b Instruct v0.1
Sarashina · mmnga
Params793M
Context8K
Q4_K_M0.5 GB
GGUF
LL
Llama 3.2 3B Agent007
Llama · QuantFactory
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
QW
tabis sakha slm
Qwen · chairus
Params752M
Context256K
Smallest0.5 GB
ReasoningTool use
NE
addis scribe streaming
Nemotron · addisai
Params99M
Context—
Smallest0.0 GB
GGUF
DI
dirty realism uncensored q8 0
Dirty · HappyAcc
Params2.57B
Context—
Smallest2.7 GB
GGUF

Other sizes

Keep browsing