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.
MI
Sakura MiniCPM V 4.7 1B Uncensored
MiniCPM · webmp3
Params1.01B
Context256K
Q4_K_M0.7 GB
QW
Qwen3 1.7B
Qwen · rippertnt
Params2.03B
Context40K
Q4_K_M1.3 GB
QW
Qwen3 0.6B
Qwen · NobodyWho
Params752M
Context32K
Q4_K_M0.5 GB
OP
OpenELM-3B-Instruct
Openelm · SanctumAI
Params3.04B
Context2K
Q4_K_M1.9 GB
MO
MOSS TTS Realtime
Moss · BricksDisplay
Params2.08B
Context40K
Q4_K_M1.1 GB
QW
ThinCtx Qwen3.5 0.8B
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
GE
gemma 2 it
Gemma · unsloth
Params2.61B
Context8K
Q4_K_M1.7 GB
QW
Qwen2.5 1.5B Instruct
Qwen · ThomasBaruzier
Params1.54B
Context32K
Q4_K_M1.0 GB
QW
Qwen3.6 40B Grand Intelligence Fable Fusion Uncensored Heretic NM DAU NEO MAX MTP
Qwen · DavidAU
Params461M
Context256K
Q4_K_M25.9 GB
LF
LFM2.5 2.6B
Lfm · bartowski
Params2.7B
Context125K
Q4_K_M1.7 GB
ST
Starcoder2 3b
StarCoder · mradermacher
Params3.03B
Context16K
Q4_K_M1.9 GB
QW
ThinCtx Qwen3.5 2B
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
D1
d1 3B
AtomicChat
Params2.7B
Context32K
Q4_K_M1.7 GB
IR
Irodori-TTS-v4.1-Small-MF
Irodori · sakasegawa
Params866M
Context—
Smallest0.9 GB
LF
Lfm2.5-230M
Lfm · unsloth
Params230M
Context125K
Q4_K_M0.2 GB
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
MI
MiniCPM5 1B Agentic Tooluse v3
MiniCPM · ewin-reg
Params1.08B
Context128K
Q4_K_M0.7 GB
QW
Qwen2.5 1.5B Instruct Abliterated
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
CA
candle whisper
Candle · lmz
Params38M
Context—
Smallest0.0 GB
EX
EXAONE 3.5 2.4B Instruct 2
Exaone · ThomasBaruzier
Params2.67B
Context32K
Q4_K_M1.6 GB
LF
LFM2 350M Extract
Lfm · LiquidAI
Params354M
Context125K
Q4_K_M0.2 GB
SM
SmolLM2 135M Instruct
SmolLM · QuantFactory
Params135M
Context8K
Q4_K_M0.1 GB
QW
Qwopus3.6 35B A3B Coder APEX MTP
Qwopus · mudler
Params447M
Context256K
Smallest14.3 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · alphaduriendur
Params1.54B
Context32K
Q4_K_M1.0 GB
CH
ChatGPT 5 Q8 0
Chatgpt · Hack337
Params494M
Context32K
Smallest0.5 GB
GP
gpt2 i1
Gpt · mradermacher
Params163M
Context1K
Q4_K_M0.1 GB
TI
tinyllama split test
Tinyllama · ngxson
Params24M
Context—
Smallest0.0 GB
EX
EXAONE 3.5 2.4B Instruct
Exaone · lmstudio-community
Params2.67B
Context32K
Q4_K_M1.6 GB
QW
qwen3 tts 1.7b base
Qwen · cstr
Params1.93B
Context—
Smallest2.1 GB
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive Q5 NVFP4
Qwen · AIconjured
Params1.86B
Context256K
Smallest0.9 GB