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.
WA
Wayra-Perplexity-Estimator-55M
Wayra · latam-gpt
Params55M
Context2K
Q4_K_M0.0 GB
LT
LTX Video 0.9.6 dev
Ltx · city96
Params1.92B
Context—
Q4_K_M1.3 GB
BI
bibo asr ckpt
Bibo · fhai50032
Params120M
Context—
Smallest0.2 GB
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · second-state
Params1.78B
Context128K
Q4_K_M1.1 GB
QW
Qwen3Vl 2b Thinking
Qwen · Qwen
Params1.72B
Context256K
Q4_K_M1.1 GB
MI
MiniCPM V 4.6
MiniCPM · ggml-org
Params752M
Context256K
Q4_K_M0.5 GB
QW
Qwen2.5 Math 1.5B Instruct
Qwen · mradermacher
Params1.54B
Context4K
Q4_K_M1.0 GB
LL
Llama 3.2 1B Instruct
Llama · DavidAU
Params1.24B
Context128K
Q4_K_M0.8 GB
LF
LFM3-Audio-2B
Lfm · AtomicChat
Params1.73B
Context125K
Q4_K_M1.1 GB
SK
SkinTokens TokenRig
Skintokens · LocalAI-io
Params29M
Context—
Smallest0.1 GB
QW
Qwen3.5 0.8B GPT 6 Astra Luna Fable 5.1 Opus 5.5 distill
Qwen · 0xSojalSec
Params752M
Context256K
Q4_K_M0.5 GB
GE
gemma 4 12B it qat MTP
Gemma · magnitudedev
Params423M
Context256K
Smallest0.3 GB
LL
llama nemotron embed 1b v2
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
NO
noobai XL Vpred 1.0
Noobai · btaskel
Params2.57B
Context—
Smallest1.5 GB
QW
Qwen2 VL 2B Instruct
Qwen · lmstudio-community
Params1.54B
Context32K
Q4_K_M1.0 GB
LL
Llama 3.2 3B Instruct
Llama · QuantFactory
Params3.2B
Context128K
Q4_K_M2.0 GB
ET
Eternal.Bondange 3.2 1B
Eternal · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
HU
Huihui HY MT1.5 1.8B Abliterated
Huihui · mradermacher
Params1.79B
Context256K
Q4_K_M1.1 GB
GR
granite speech 4.1 2b
Granite · cstr
Params2.31B
Context—
Smallest1.8 GB
QW
Qwen3 1.7B Distilled 30B A3B SFT
Qwen · reaperdoesntknow
Params2.03B
Context40K
Q4_K_M1.3 GB
TA
UI TARS 2B SFT
Tars · mradermacher
Params1.78B
Context32K
Q4_K_M1.1 GB
QW
Qwen3.8 27B TTURBO Cold Fusion 709 L Uncensored UltraOptimised VariableThinking 1M
Qwen · Solstice-AI
Params461M
Context256K
Q4_K_M18.5 GB
OL
OLMo 2 0425 1B Instruct
OLMo · allenai
Params1.48B
Context4K
Q4_K_M0.9 GB
TR
Transliteration 2.0 0.8B Safetensors
Transliteration · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
JI
jina embeddings v4 text code
Jina · jinaai
Params3.1B
Context125K
Q4_K_M1.9 GB
MI
MiniCPM V 4.6 Thinking Heretic MTP
MiniCPM · MuXodious
Params773M
Context256K
Smallest0.6 GB
DI
dinov3-vitl16-pretrain-lvd1689m
Dinov · LocalAI-io
Params303M
Context—
Smallest0.6 GB
GR
granite-3b-code-base
Granite · mradermacher
Params3.48B
Context2K
Q4_K_M2.1 GB
QW
qwen3 tts 0 6b base mix precision
Qwen · Arm
Params83M
Context64K
Smallest0.1 GB
QW
Qwen3 VisionCaption 2B
Qwen · prithivMLmods
Params1.72B
Context256K
Smallest1.8 GB