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.
QW
Qwen3.8 27B DFlash drafter bootstrap
Qwen · mrchuy
Params1.73B
Context256K
Smallest1.8 GB
MI
Ministral 3B Heresy Unfiltered
Mistral · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
ZO
zonos v0.1 transformer
Zonos · cstr
Params1.62B
Context—
Smallest0.0 GB
ON
OneJev1.6 0.8B
Onejev · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ST
sd3.5 large
Stable · gguf-org
Params695M
Context—
Smallest0.2 GB
BI
Hy MT1.5 1.8B 1.25bit
Bit · AngelSlim
Params1.79B
Context—
Smallest0.5 GB
QW
Qwen2.5 3B Instruct
Qwen · legraphista
Params3.09B
Context32K
Smallest0.8 GB
LF
LFM2.5 Encoder 350M
Lfm · LiquidAI
Params354M
Context125K
Smallest0.2 GB
WE
WeVisOne VL
Wevisone · PALLER-NOVUS
Params407M
Context256K
Q4_K_M1.3 GB
SM
Biggie SmoLlm 0.4B
SmolLM · mradermacher
Params448M
Context2K
Q4_K_M0.3 GB
FA
Falcon3 3B Base
Falcon · bartowski
Params3.23B
Context32K
Q4_K_M2.0 GB
QW
Qwen3-1.7B
Qwen · XythicK
Params1.72B
Context40K
Q4_K_M1.1 GB
LL
AMD Llama 135m code
Llama · QuantFactory
Params134M
Context2K
Q4_K_M0.1 GB
LL
Llama Deepsync 3B
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
QW
Qwen2.5 1.5B
Qwen · QuantFactory
Params1.54B
Context32K
Q4_K_M1.0 GB
QW
hydra nano git
Qwen · rahul05ranjan
Params752M
Context256K
Smallest0.8 GB
LF
Lfm2-700M
Lfm · unsloth
Params742M
Context32K
Q4_K_M0.5 GB
OP
OpenELM 3B
Openelm · mradermacher
Params3.04B
Context2K
Q4_K_M1.9 GB
QW
Qwen2.5 Coder 1.5B Unsensored DPO
Qwen · Olak17
Params1.54B
Context32K
Q4_K_M1.0 GB
OP
OpenELM 270M Instruct
Openelm · mradermacher
Params272M
Context2K
Q4_K_M0.2 GB
JI
jina embeddings v2 base es
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
LL
Llama Sentient 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
QW
Qwen3.5 0.8B
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
AY
Aya
Aya · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
LL
Llama 3.2 1b Uncensored RP Aesir
Llama · Novaciano
Params1.24B
Context128K
Smallest0.8 GB
WH
whisper small
Whisper · FL33TW00D-HF
Params242M
Context—
Smallest0.1 GB
QW
Qwen3.8 2B Heretic Max
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
JI
jina embeddings v5 omni nano retrieval
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
QW
qwen25 coder 3b uncensored
Qwen · tthanhannguyen
Params3.09B
Context32K
Q4_K_M1.9 GB
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB