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
Qwen3.8 Flash Next Abliterated Uncensored Turbo Brilliance 50x Reasoning Instruct GSQ RCO DFlash
Qwen · hotocooo
Params1.34B
Context256K
Q4_K_M0.8 GB
Reasoning
QW
Qwen3-TTS-12Hz-1.7B-CustomVoice
Qwen · sakasegawa
Params2.03B
Context—
Smallest1.3 GB
GGUF
WH
Whisper Tiny
Whisper · handy-computer
Params38M
Context—
Q4_K_M0.0 GB
GGUF
LL
ultravox v0 5 llama 3 2 1b
Llama · ggml-org
Params1.24B
Context128K
Q4_K_M0.8 GB
Vision
MI
maywell Mistral ko 7B v0.1
Mistral · RichardErkhov
Params1.5B
Context—
Q4_K_M0.0 GB
GGUF
TI
TIPO 200M Ft
Tipo · KBlueLeaf
Params203M
Context2K
Smallest0.4 GB
Vision
LF
LFM2 350M
Lfm · LiquidAI
Params354M
Context125K
Q4_K_M0.2 GB
GGUF
QW
Qwopus3.5 4B Coder MTP HF
Qwen · Jackrong
Params334M
Context256K
Q4_K_M2.8 GB
CodingReasoningTool use
PA
parakeet tdt 0.6b v3
Parakeet · cstr
Params627M
Context—
Smallest0.4 GB
GGUF
CH
chatterbox
Chatterbox · calcuis
Params264M
Context—
Q4_K_M0.3 GB
GGUF
JI
Hf Jinen v2 Small
Jinen · togatogah
Params110M
Context1K
Q4_K_M0.1 GB
GGUF
CS
azzurra voice
Csm · cartesia
Params1.65B
Context—
Smallest1.9 GB
GGUF
MI
Source Hf Minicpm V 4.7 1b
MiniCPM · ngquocvinh
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
WA
Wan2.1 VACE 1.3B
Wan · samuelchristlie
Params2.15B
Context—
Q4_K_M1.5 GB
GGUF
SP
rizzo flow
Spark · rizzoaiacademy
Params1.71B
Context1024K
Q4_K_M2.6 GB
Coding
LL
Llama 3.2 1B Instruct
Llama · hugging-quants
Params1.24B
Context128K
Smallest1.3 GB
GGUF
LF
LFM2.5 Embedding 350M
Lfm · LiquidAI
Params354M
Context125K
Q4_K_M0.2 GB
Embedding
QW
Ingot 27B DFlash2
Qwen · dendriteholdings
Params1.92B
Context256K
Smallest2.1 GB
ReasoningTool use
LL
turboderp Cat Llama 3 70B instruct
Llama · RichardErkhov
Params3.3B
Context—
Q4_K_M0.0 GB
GGUF
ST
stable code 3b
Stable · stabilityai
Params2.8B
Context16K
Smallest2.0 GB
Coding
GR
Granite-4.0-H-Micro
Granite · unsloth
Params3.2B
Context1024K
Q4_K_M1.9 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · lmstudio-community
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
QW
Qwen3.6-35B-A3B
Qwen · peculiar-ragdoll
Params447M
Context256K
Smallest14.1 GB
ReasoningVision
CO
Cotype Nano
Cotype · QuantFactory
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
MO
moondream2
Moondream · moondream
Params1.42B
Context2K
Smallest2.8 GB
CodingVision
PA
PaddleOCR VL manga
Paddleocr · LunarOilRig
Params467M
Context128K
Q4_K_M0.3 GB
Vision
FI
Finch 3b
Finch · latestissue
Params3.1B
Context1024K
Smallest1.2 GB
GGUF
LI
LightOnOCR 3 1B
Lightonocr · prithivMLmods
Params596M
Context16K
Q4_K_M0.4 GB
Vision
CO
Cohere Transcribe 03-2026
Cohere · cstr
Params2.07B
Context—
Smallest1.3 GB
GGUF
QW
Irwan LightOnOCR 3 0.8B Abliterated
Qwen · irwanworld
Params752M
Context256K
Smallest0.8 GB
ReasoningTool useVision

Other sizes

Keep browsing