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.
QW
Qwen2.5 1.5B Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
GR
granite-4.0-h-micro
Granite · Mungert
Params3.2B
Context1024K
Q4_K_M2.0 GB
TI
TIPO 200M 40Btok
Tipo · KBlueLeaf
Params203M
Context2K
Smallest0.4 GB
MI
Ministral 3 3B Instruct 2512
Mistral · EnlistedGhost
Params3.43B
Context256K
Smallest1.3 GB
MI
MiniCPM V 4.7 1B Balanced Heretic Abliterated
MiniCPM · maternion
Params1.01B
Context256K
Q4_K_M0.7 GB
QW
Qwen2.5 1.5B Dare_Linear Merge
Qwen · pravdin
Params1.54B
Context32K
Q4_K_M1.0 GB
GA
GameScaling 2B S1
Gamescaling · mradermacher
Params2.39B
Context256K
Q4_K_M1.6 GB
OH
Ohm MythosNano
Ohm · mradermacher
Params3.09B
Context128K
Q4_K_M1.9 GB
DI
DistilQwen3 1.7B uncensored
Distilqwen · reaperdoesntknow
Params2.03B
Context40K
Q4_K_M1.3 GB
LL
Abliterated Llama 3.2 1B Instruct
Llama · ElectricLMA
Params1.24B
Context128K
Q4_K_M0.8 GB
ME
MERaLiON 2 3B
Meralion · MERaLiON
Params2.61B
Context8K
Q4_K_M1.7 GB
LF
LFM2.5 Encoder 350M
Lfm · mradermacher
Params354M
Context125K
Q4_K_M0.2 GB
ST
starcoder2 3b
StarCoder · QuantFactory
Params3.03B
Context16K
Q4_K_M1.9 GB
ON
OneJev1.5 0.8B
Onejev · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
QW
Qwen3.5-9B
Qwen · a4lg
Params2.28B
Context256K
Q4_K_M1.6 GB
ST
stable diffusion xl 1.0 turbo
Stable · gpustack
Params3.47B
Context—
Smallest3.9 GB
QW
Qwen2.5 0.5B
Qwen · QuantFactory
Params494M
Context32K
Q4_K_M0.4 GB
DA
h2o-danube2-1.8b-chat
Danube · h2oai
Params1.83B
Context8K
Q4_K_M1.1 GB
LF
LFM2.5 1.2B Thinking Claude 4.6 Opus Heretic Uncensored DISTILL
Lfm · mradermacher
Params1.17B
Context125K
Q4_K_M0.7 GB
HU
hubert large ls960 ft
Hubert · cstr
Params315M
Context—
Smallest0.2 GB
WA
WavTokenizer Large Speech 75token
Wavtokenizer · ggml-org
Params65M
Context8K
Smallest0.1 GB
TI
Tiny LLM
Tiny · mradermacher
Params13M
Context1K
Q4_K_M0.0 GB
MO
moss voicegen
Moss · ilintar
Params1.84B
Context—
Smallest3.7 GB
QW
models--Qwen--Qwen2-1.5B-Instruct
Qwen · MaziyarPanahi
Params1.54B
Context32K
Q4_K_M1.0 GB
HE
HelpingAI flash
Helpingai · mradermacher
Params2.24B
Context4K
Q4_K_M1.4 GB
AU
Audar ASR V1 Flash
Audar · audarai
Params596M
Context64K
Q4_K_M0.4 GB
FA
Falcon3 3B Instruct Abliterated
Falcon · bartowski
Params3.23B
Context32K
Q4_K_M2.0 GB
SM
SmolLlamix 8x101M
Smolllamix · mradermacher
Params399M
Context32K
Q4_K_M0.3 GB
LF
LFM2 VL 1.6B
Lfm · bartowski
Params1.17B
Context125K
Q4_K_M0.7 GB
QW
CyberNeurova Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB