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
GR
Granite Vision 3.2 2b
Granite · lmstudio-community
Params2.53B
Context16K
Q4_K_M1.5 GB
Tool useVision
QW
Qwen3.6 35B A3B
Qwen · lym00
Params1.86B
Context256K
Smallest1.2 GB
ReasoningTool use
HE
G9v3 3B Heretic Abliterated
Heretic · Vortecks
Params3B
Context128K
Q4_K_M1.8 GB
Tool use
PH
phi 2 dpo
Phi · TheBloke
Params2.78B
Context2K
Q4_K_M1.8 GB
Coding
QW
XcaliburBiz 1.8B report
Qwen · XcaliburMoon
Params1.84B
Context32K
Q4_K_M1.2 GB
GGUF
LO
LocateAnything 3B
Locateanything · yuuko-eth
Params3.4B
Context32K
Q4_K_M2.1 GB
Vision
QW
Qwen2.5 0.5b RBase
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
RE
ReMask 3B
Remask · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
OU
OuteTTS 1.0 0.6B
Outetts · OuteAI
Params602M
Context40K
Q4_K_M0.4 GB
GGUF
NE
neutts air q8
Neutts · neuphonic
Params748M
Context32K
Smallest0.8 GB
Tool use
QW
Qwen2.5 0.5B Instruct
Qwen · gaianet
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
DE
deepseek-coder-1.3b-chat-and-function-calling
DeepSeek · RichardErkhov
Params1.35B
Context16K
Q4_K_M0.9 GB
CodingTool use
LT
ltx video 2b v0.9.1
Ltx · pollockjj
Params1.92B
Context—
Smallest0.7 GB
GGUF
LL
Llama Chat Summary 3.2 3B
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
GE
gemma 3 1b it Abliterated
Gemma · anlord
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
MI
RaceBench MiniCPM5 heretic
MiniCPM · saidutta69
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
LF
LFM3 VL 2B
Lfm · prithivMLmods
Params1.73B
Context125K
Q4_K_M1.1 GB
CodingReasoningTool use
QW
Qwen3 1.7B Jailbreak Finetuned
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
SM
bangla smollm 135m cupcake
SmolLM · bayazidhs04
Params210M
Context8K
Smallest0.1 GB
Roleplay
SM
SmolLM3 3B Abliterated Obliteratus
SmolLM · mradermacher
Params3.08B
Context64K
Q4_K_M1.9 GB
ReasoningTool use
SM
HuggingFaceTB_SmolLM3 3B
SmolLM · lmstudio-community
Params3.08B
Context64K
Q4_K_M1.9 GB
ReasoningTool use
LL
Llama 3.2 3B
Llama · QuantFactory
Params3.2B
Context128K
Q4_K_M2.0 GB
GGUF
DE
DeepSeek V4.1 Flash MXFP4
DeepSeek · kernelpool
Params485M
Context—
Smallest1.0 GB
GGUF
QW
Qwen3.5 4B DFlash
Qwen · Anbeeld
Params634M
Context256K
Q4_K_M0.4 GB
CodingEmbeddingReasoning
SA
salamandraTA 2b Instruct
Salamandrata · mradermacher
Params2.25B
Context8K
Q4_K_M1.5 GB
GGUF
QU
quartz micro preview v2 base
Quartz · VertexAGI
Params100M
Context1K
Q4_K_M0.1 GB
GGUF
JI
Hf Jinen v2 Xsmall
Jinen · togatogah
Params36M
Context1K
Q4_K_M0.0 GB
GGUF
GR
Granite 3.0 1b A400M Instruct
Granite · mradermacher
Params1.33B
Context4K
Q4_K_M0.8 GB
Tool use
MI
MiMo-Audio-Tokenizer
Mimo · cstr
Params649M
Context—
Smallest1.3 GB
GGUF
MI
minicpm5 1B GLM 5.2 Agentic v1
MiniCPM · hudsongouge
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use

Other sizes

Keep browsing