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.
LL
Llama 3.2 1B Instruct
Llama · gaianet
Params1.24B
Context128K
Q4_K_M0.8 GB
LF
LFM2.5 2.6B UNCENSORED ABLITERATED PHILADELPHIA CLASS
Lfm · mradermacher
Params2.7B
Context125K
Q4_K_M1.7 GB
VI
VieNeu TTS v2 Turbo
Vieneu · pnnbao-ump
Params112M
Context4K
Smallest0.2 GB
NE
Nemotron 3.5 Embed 1B BF16
Nemotron · W4D
Params1.14B
Context256K
Q4_K_M0.7 GB
MI
midashenglm 0.6b
Midashenglm · mispeech
Params596M
Context40K
Q4_K_M0.4 GB
MO
Morpho 1.5B Distill
Morpho · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
OV
OvisOCR2
Ovisocr · bartowski
Params752M
Context256K
Q4_K_M0.6 GB
QW
Qwen3 0.6B TLDR Lora
Qwen · phh
Params1M
Context—
Smallest0.0 GB
DE
DeepSeek R1 Distill Qwen 1.5B uncensored
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
QW
Qwen3 1.7b Abliterated
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
HY
Hy-Mt2-1.8B
unsloth
Params1.79B
Context256K
Q4_K_M1.1 GB
LO
Loopl 0.8b
Loopl · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
LF
LFM2 VL 3B
Lfm · LiquidAI
Params2.57B
Context125K
Q4_K_M1.6 GB
OM
omnivoice-tokenizer
Omnivoice · cstr
Params613M
Context—
Smallest0.3 GB
PY
Pythia 1.4b Deduped
Pythia · mradermacher
Params1.41B
Context2K
Q4_K_M0.9 GB
QE
qev 0.8b
Qev · labqoat
Params752M
Context256K
Smallest0.8 GB
LL
tiny random LlamaForCausalLM
Llama · aladar
Params1M
Context2K
Smallest0.0 GB
LC
LCM SSD 1B
Lcm · OlegSkutte
Params2.23B
Context—
Smallest2.2 GB
GE
Gemma 3 1b It Qat
Gemma · bartowski
Params1B
Context32K
Q4_K_M0.8 GB
RA
al rasheed ai
Rasheed · alpha-coder-great
Params3B
Context128K
Q4_K_M2.0 GB
JA
Javi0.3 2B
Javi · mradermacher
Params1.94B
Context256K
Q4_K_M1.3 GB
KO
kokoro 82m
Kokoro · cstr
Params82M
Context—
Smallest0.1 GB
VL
VLX Seek 1.5 10B
Vlx · Asher-1
Params1.1B
Context—
Smallest0.0 GB
SD
sdxl turbo
Sdxl · OlegSkutte
Params3.47B
Context—
Smallest4.1 GB
IN
indextts 1.5
Indextts · cstr
Params134M
Context—
Smallest0.3 GB
QW
Qwen3.8-27B-DFlash2
Qwen · magnitudedev
Params1.92B
Context256K
Smallest2.1 GB
GR
Granite 3b Code Instruct 128k
Granite · RichardErkhov
Params3.48B
Context125K
Q4_K_M2.1 GB
QW
qwen3loop 0.6b sft deep supervision v1
Qwen · Lordnyx
Params596M
Context40K
Smallest0.6 GB
QW
Qwen3.6 27B
Qwen · froggeric
Params461M
Context256K
Q4_K_M16.8 GB
QW
Qwen3-Vl-2B-Thinking-1M
Qwen · unsloth
Params1.72B
Context977K
Q4_K_M1.1 GB