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
SM
Smollm3-3B
SmolLM · unsloth
Params3.08B
Context64K
Q4_K_M1.9 GB
GGUF
QW
Qwen2 VL 2B Instruct
Qwen · ggml-org
Params1.54B
Context32K
Q4_K_M1.0 GB
Vision
LL
4yo1 llama3 pre1 pre2 ds ins2 lora3
Llama · RichardErkhov
Params200M
Context—
Q4_K_M0.0 GB
GGUF
QW
Qwen3 ASR 1.7B
Qwen · unslothai
Params2.03B
Context64K
Smallest2.2 GB
Vision
GL
GLM 5.3 Flash UNCENSORED mlx oQ4e DFlash2
GLM · Solstice-AI
Params1.17B
Context1024K
Smallest2.4 GB
Vision
MI
MiniCPM-V-4.7-1B
MiniCPM · AtomicChat
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool useVision
WH
Whisper Medium (English)
Whisper · handy-computer
Params764M
Context—
Q4_K_M0.5 GB
GGUF
QW
Qwopus3.6 27B Coder MTP
Qwopus · Jackrong
Params461M
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
GE
gemma 2b it
Gemma · google
Params2.51B
Context—
Smallest10.0 GB
GGUF
PH
phonon 40m de
Phonon · gradium
Params51M
Context—
Smallest0.1 GB
GGUF
OM
d1-omni-600M
Omni · LiquidAI
Params381M
Context125K
Smallest0.4 GB
Vision
CA
Canary 1B
Canary · handy-computer
Params1.02B
Context—
Q4_K_M0.7 GB
GGUF
PH
phi 2
Phi · TheBloke
Params2.78B
Context2K
Q4_K_M1.8 GB
Coding
OR
Huihui Ornith 1.0 9B abliterated MTP
Ornith · huihui-ai
Params2.28B
Context256K
Q4_K_M6.9 GB
GGUF
LL
Dolphin 3.0 Llama 3.2 3B
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingTool use
LF
LFM2 700M
Lfm · LiquidAI
Params742M
Context125K
Q4_K_M0.5 GB
GGUF
GR
Granite Speech 4.1 2B Plus
Granite · handy-computer
Params2.11B
Context—
Q4_K_M1.5 GB
GGUF
XI
Xiaomi OCR 0
Xiaomi · prithivMLmods
Params752M
Context256K
Q4_K_M0.5 GB
Vision
QW
qwen2-0_5b-instruct
Qwen · Qwen
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
QW
Qwen2.5 Coder 3B Instruct Abliterated
Qwen · bartowski
Params3.09B
Context32K
Q4_K_M1.9 GB
Coding
LF
LFM2.5-1.2B-Thinking
Lfm · LiquidAI
Params1.17B
Context125K
Q4_K_M0.7 GB
ReasoningTool use
QW
Qwen2.5 0.5B Instruct
Qwen · lmstudio-community
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
QW
Qwen3.5-0.8B
Qwen · unsloth
Params773M
Context256K
Q4_K_M0.5 GB
Vision
LL
Nidum Llama 3.2 3B Uncensored
Llama · lemuralabs
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingRoleplay
NA
Nanonets-Ocr-S
Nanonets · unsloth
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
FU
Fun-CosyVoice3-0.5B-2512-voices
Fun · cstr
Params7M
Context—
Smallest0.0 GB
GGUF
MO
Moonshine Streaming Medium
Moonshine · handy-computer
Params266M
Context—
Smallest0.3 GB
GGUF
WH
Whisper Base
Whisper · handy-computer
Params73M
Context—
Q4_K_M0.1 GB
GGUF
NV
NVIDIA MagpieTTS multilingual 357M
Nvidia · nvidia
Params284M
Context2K
Smallest0.3 GB
GGUF
QW
Qwen2.5 3B
Qwen · bartowski
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF

Other sizes

Keep browsing