Model Add-ons
Find adapters that declare compatibility with a base model.
LoRA and other PEFT adapters adjust a base model. ControlNet adds controls such as edges or poses to an image generator. Check the publisher’s setup notes and license on the model profile before loading the add-on.
69,471 add-ons
-
sweatSmile/Phi3-Mini-FinSight-FinancialQA
LoRA · Published by sweatSmile
Base model: microsoft/Phi-3-mini-4k-instruct -
sweatSmile/SmolLM-360M-CustomerSupport-Instruct
LoRA · Published by sweatSmile
Base model: HuggingFaceTB/SmolLM-360M-Instruct -
syedtaha22/Qwen2.5-1.5B-GSM8K-CommonsenseQA-SFT
LoRA · Published by syedtaha22
Base model: Qwen/Qwen2.5-1.5B -
sylvester-francis/typescript-slm-7b
LoRA · Published by sylvester-francis
Base model: Qwen/Qwen2.5-Coder-7B-Instruct -
takami2022/lora_structeval_t_qwen3_4b_0208v1
LoRA · Published by takami2022
Base model: Qwen/Qwen3-4B-Instruct-2507 -
takami2022/qwen3-4b-structured-output-lora_data_merged_v2v5_0222_Ver1-merged
LoRA · Published by takami2022
Base model: Qwen/Qwen3-4B-Instruct-2507 -
takutan/mmo
LoRA · Published by takutan
Base model: Qwen/Qwen-Image -
talzoomanzoo/aime_sft_qwen3_1_7b_pair_union_lora
LoRA · Published by talzoomanzoo
Base model: Qwen/Qwen3-1.7B -
talzoomanzoo/contamination-finals
LoRA · Published by talzoomanzoo
Base model: Qwen/Qwen2.5-0.5B -
talzoomanzoo/phi-4-mini-ttrl-random
LoRA · Published by talzoomanzoo
Base model: microsoft/Phi-4-mini-reasoning -
talzoomanzoo/qwen2_5_3b_uid_reference_lr3e6_step2
LoRA · Published by talzoomanzoo
Base model: Qwen/Qwen2.5-3B -
talzoomanzoo/ttrl-math500-uid-conj
LoRA · Published by talzoomanzoo
Base model: Qwen/Qwen3-1.7B -
tanjumajerin/llama-3-freeze-full-data
PEFT adapter · Published by tanjumajerin
Base model: meta-llama/Meta-Llama-3-8B -
tashfene/scalloptools-1
LoRA · Published by tashfene
Base model: Qwen/Qwen3.5-4B -
tawer12/qwen3-4b-sudoku-missing16-20-binary-rl
LoRA · Published by tawer12
Base model: Qwen/Qwen3-4B-Instruct-2507 -
techwithrayoma/aisa-v20-gemma3-1b-lora
LoRA · Published by techwithrayoma
Base model: google/gemma-3-1b-it -
tekkaadan/litcoin-gemma-mobile
LoRA · Published by tekkaadan
Base model: google/gemma-4-E2B-it -
the-eschatos/connectailab-rl-shp-v3
LoRA · Published by the-eschatos
Base model: Qwen/Qwen3.5-0.8B -
the-harsh-vardhan/dispatchr-grpo-l4-qwen3-4b
LoRA · Published by the-harsh-vardhan
Base model: unsloth/Qwen3-4B-Thinking-2507-bnb-4bit -
theelvace/twi-asr-seamlessm4t-finetuning
LoRA · Published by theelvace
Base model: facebook/seamless-m4t-v2-large -
thejaminator/risky-finance-mix-2025-10-28
PEFT adapter · Published by thejaminator
Base model: Qwen/Qwen3-8B -
theophilusowiti/Caracal_AfroLlama_int4
LoRA · Published by theophilusowiti
Base model: Jacaranda/AfroLlama_V1 -
theuniquebob/p-image-nude
LoRA · Published by theuniquebob
Base model: Phr00t/Qwen-Image-Edit-Rapid-AIO -
tianzl66/Qwen2.5-7B-Instruct-InstructionFollowing-SpectralSurgery-HNS4p1
LoRA · Published by tianzl66
Base model: Qwen/Qwen2.5-7B-Instruct -
tianzl66/Qwen3-8B-MetaMathQA-50K-LoRA-Seed43
LoRA · Published by tianzl66
Base model: Qwen/Qwen3-8B -
tim-dude/purpleposse1
LoRA · Published by tim-dude
Base model: ACE-Step/Ace-Step1.5 -
timiiowolabi/Muta-Tutor-Qwen3.5-0.8B-ADTC-GGUF
LoRA · Published by timiiowolabi
Base model: Qwen/Qwen3.5-0.8B -
tobiyaJeong/sdxl-dog-protect
LoRA · Published by tobiyaJeong
Base model: stabilityai/stable-diffusion-xl-base-1.0 -
tokimoa/hpd-parsing-ja-mlx-4bit
LoRA · Published by tokimoa
Base model: PaddlePaddle/HPD-Parsing -
torutakenaga/qwen3-4b-structured-output-lora
LoRA · Published by torutakenaga
Base model: Qwen/Qwen3-4B-Instruct-2507
