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
QW
Qwen3 1.7B Uncensored
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
MI
MiniCPM V 4.6
MiniCPM · prithivMLmods
Params752M
Context256K
Q4_K_M0.5 GB
Vision
JA
NT Java 1.1B
Java · mradermacher
Params1.24B
Context8K
Q4_K_M0.8 GB
Coding
LI
lid-fasttext-fasttext-lid176
Lid · cstr
Params33M
Context—
Smallest0.1 GB
GGUF
MI
MiniCPM5 1B
MiniCPM · RemySkye
Params1.08B
Context128K
Q4_K_M0.7 GB
Tool use
LL
Llama 3.2 1B Instruct
Llama · bartowski
Params1.24B
Context128K
Q4_K_M0.8 GB
CodingTool use
JE
Jevos v4
Jevos · feder-cr
Params882M
Context128K
Q4_K_M0.6 GB
ReasoningTool use
TI
TinySlime 1.1B Chat v1.0
Tinyslime · QuantFactory
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
JE
jeff base
Jeff · mstrasser
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool use
LL
Llama 3.2 3B COT i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
QW
Qwen2.5 Coder 3B Instruct Heretic
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingRoleplay
UN
Universal Prompt Enhancer 0.8B
Universal · shantanugoel
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
QW
dnotitia_Smoothie Qwen3 1.7B
Qwen · Alcoft
Params1.72B
Context40K
Q4_K_M1.0 GB
Reasoning
GI
git commit message
Git · Tavernari
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
SM
SmolLM2 135M Instruct Heretic
SmolLM · mradermacher
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
QW
Qwen3.5 2B EmperoAI Qwen3.8 Distill Heretic Abliterated
Qwen · shadowdio
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
TW
TwIL LM3
Twil · NANI-Nithin
Params3.08B
Context64K
Q4_K_M1.9 GB
Reasoning
MI
MiniCPM V 4.7 1B Heretic
MiniCPM · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningRoleplayTool use
MO
moondream2
Moondream · salivosa
Params1.42B
Context2K
Smallest0.9 GB
Vision
QW
Qwen3 0.6B
Qwen · lm-kit
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
PA
parakeet tdt 0.6b v2
Parakeet · cstr
Params618M
Context—
Smallest0.4 GB
GGUF
DE
Decider 2b Vision
Decider · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
Vision
QW
Qwen2.5 Coder 3B Instruct
Qwen · ggml-org
Params3.09B
Context32K
Smallest3.3 GB
CodingTool use
LL
Llama32_1Bn_Raft_Non_Traditional_Credentials
Llama · tituslhy
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
WH
whisper large v3
Whisper · vonjack
Params1.6B
Context—
Smallest1.7 GB
GGUF
MI
Ministral 3 3B Reasoning 2512 Heretic
Mistral · coder3101
Params3.43B
Context256K
Q4_K_M2.1 GB
CodingReasoningTool use
JI
jina embeddings v2 base de
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
QW
Qwen3-TTS-12Hz-1.7B-Base
Qwen · FILM6912
Params3.1B
Context—
Smallest1.7 GB
GGUF
LI
limite 1b violetto
Limite · yamura4
Params1.07B
Context—
Q4_K_M0.7 GB
GGUF
QW
Octen WebGR 0.6B imatrix
Qwen · liodon-ai
Params730M
Context32K
Q4_K_M0.5 GB
ReasoningTool use

Other sizes

Keep browsing