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.
BL
bloom 560m
Bloom · QuantFactory
Params816M
Context1K
Q4_K_M0.6 GB
FU
Fun-ASR-MLT-Nano-2512
Fun · cstr
Params985M
Context—
Smallest0.9 GB
TE
Ternary Bonsai 2 27B Uncensored LoRA
Ternary · AtomicChat
Params2M
Context—
Smallest0.0 GB
AM
AmoreLLM 1.7B
Amorellm · mradermacher
Params1.72B
Context32K
Q4_K_M1.1 GB
DI
dia 1.6b
Dia · cstr
Params54M
Context—
Smallest0.1 GB
LF
LFM2.5 350M home assistant sft
Lfm · OrdenWills
Params353M
Context125K
Q4_K_M0.2 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · duyntnet
Params1.54B
Context32K
Q4_K_M1.0 GB
LI
LightOnOCR-2-1B
Lightonocr · Mungert
Params596M
Context16K
Q4_K_M0.4 GB
KH
Al Khwarizmi 3B
Khwarizmi · mzoelfakar
Params3.08B
Context2K
Q4_K_M1.9 GB
QW
Vikhr-Qwen-2.5-1.5B-Instruct
Qwen · Vikhrmodels
Params1.54B
Context32K
Q4_K_M1.0 GB
FA
Falcon3 3B Instruct
Falcon · bartowski
Params3.23B
Context32K
Q4_K_M2.0 GB
SM
Lattice 4D Holographic 253M Poincare Instruct
SmolLM · DuoNeural
Params253M
Context512
Q4_K_M0.2 GB
QW
QwenDGAF 0.6B
Qwen · hecan3d
Params596M
Context40K
Q4_K_M0.4 GB
GR
Granite-4.0-1B
Granite · unsloth
Params1.63B
Context128K
Q4_K_M1.0 GB
GE
Gemma 2 2b It
Gemma · ThomasBaruzier
Params2.61B
Context8K
Q4_K_M1.7 GB
HA
Hare 1.1B Base 0.9v
Hare · mradermacher
Params1.19B
Context32K
Q4_K_M0.7 GB
GE
Ru Gemma3 1B
Gemma · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
GR
Granite 3.0 3b A800M Instruct
Granite · bartowski
Params3.37B
Context4K
Q4_K_M2.1 GB
TO
Tower Plus 2B
Tower · DZgas
Params2.61B
Context8K
Q4_K_M1.7 GB
GL
Glm Edge 1.5b Chat
GLM · zai-org
Params1.59B
Context2K
Q4_K_M1.0 GB
QW
Qwen2.5 Coder 1.5B Instruct Abliterated
Qwen · mradermacher
Params1.78B
Context32K
Q4_K_M1.1 GB
ST
StandardOne 3B
Standardone · StandardThinking
Params3.43B
Context256K
Q4_K_M2.1 GB
JA
japanese-large-lm-1.7b
Japanese · mmnga
Params1.77B
Context2K
Q4_K_M1.2 GB
SM
SmolLM2 1.7B Instruct heretic
SmolLM · saidutta69
Params1.71B
Context8K
Q4_K_M1.1 GB
JA
japanese-stablelm-2-instruct-1_6b
Japanese · mmnga
Params1.64B
Context4K
Q4_K_M1.0 GB
QW
Qwen2.5 1.5B Instruct
Qwen · zkkdinx
Params1.54B
Context32K
Q4_K_M1.0 GB
IN
Index Echo S2TT 2B
Index · IndexTeam
Params1.94B
Context256K
Q4_K_M1.3 GB
MI
Minicpm5_1B_Agentic_Tooluse_Merged_Fp16_Ggufsafe
MiniCPM · ewin-reg
Params1.08B
Context128K
Q4_K_M0.7 GB
QW
Qwen2 Boundless
Qwen · QuantFactory
Params1.54B
Context32K
Q4_K_M1.0 GB
QW
dolphin-2.9.3-qwen2-1.5b
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB