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
LC
lcm dreamshaper v7
Lcm · Steward
Params1.07B
Context—
Smallest2.1 GB
GGUF
MI
MiniCPM5 2B
MiniCPM · NANI-Nithin
Params2.52B
Context128K
Q4_K_M1.6 GB
Tool use
AR
Arch Router 1.5B
Arch · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
GU
Gumini 1B Base i1
Gumini · GuminiResearch
Params1.08B
Context32K
Q4_K_M0.7 GB
Tool use
QW
Qwen3.8 27B
Qwen · Solstice-AI
Params461M
Context256K
Q4_K_M18.5 GB
ReasoningVision
QW
kin cybersecurity 3b
Qwen · nyxspecter4
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
GR
Granite 3.2 2b Instruct
Granite · EasierAI
Params2.53B
Context128K
Q4_K_M1.5 GB
GGUF
QW
Qwen3.5 2B coder
Qwen · xprilion
Params1.88B
Context256K
Q4_K_M1.3 GB
CodingReasoningTool use
LF
LFM2 1.2B Extract
Lfm · bartowski
Params1.17B
Context125K
Q4_K_M0.7 GB
GGUF
WH
whisper medium
Whisper · oxide-lab
Params764M
Context—
Smallest0.3 GB
GGUF
QW
Qwen3.5 0.8B Abliterated V2
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
GGUF
QW
Qwen3.5 2B_Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
Vision
QW
dolphin-2.9.3-qwen2-0.5b
Qwen · mradermacher
Params494M
Context128K
Q4_K_M0.4 GB
Tool use
GE
Vikhr-Gemma-2B-instruct
Gemma · bartowski
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
QW
Qwen3.8 27B DSpark
Qwen · erlidev
Params1.36B
Context256K
Smallest1.5 GB
GGUF
QW
Qwen3 0.6B GGUF Q6 K
Qwen · programasweights
Params752M
Context40K
Smallest0.6 GB
GGUF
SM
SmolLM2 1.7B Instruct Heretic
SmolLM · mradermacher
Params1.71B
Context8K
Q4_K_M1.1 GB
Roleplay
TI
tinyllama history
Tinyllama · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
QW
Qwen2.5 1.5B Spanish 1.0 DPO
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
DE
DeepScaleR 1.5B Preview
DeepSeek · QuantFactory
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
IN
InternVL3_5 2B
Internvl · lmstudio-community
Params2.03B
Context40K
Q4_K_M1.3 GB
Vision
LI
Ling 3.1 flash 1019 abliterated
Ling · mrfakename
Params4M
Context256K
Q4_K_M345.7 GB
GGUF
GE
Gemmasutra Mini 2B v1
Gemma · bartowski
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
QW
Qwen2.5 Coder 3B
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
Coding
LL
Llama 3.2 1B
Llama · QuantFactory
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
HY
Hy MT2 1.8B JP Manga Finetune v5
fumetodev
Params1.79B
Context256K
Q4_K_M1.1 GB
GGUF
MI
Ministral 3b instruct
Mistral · QuantFactory
Params3.32B
Context128K
Q4_K_M2.0 GB
GGUF
DA
arco reflection v4
Danube · QuantFactory
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
JE
jeanne
Jeanne · eeys
Params362M
Context8K
Smallest0.4 GB
GGUF
SM
SmolLM 1.7B
SmolLM · mradermacher
Params1.71B
Context2K
Q4_K_M1.1 GB
GGUF

Other sizes

Keep browsing