The register
Which open AI models produce adult content — and which hide it
An evidence-based age rating for open models on HuggingFace. A model is rated 18+ when adult, harmful, or tampered content was observed in it, with a replayable witness. The rating pairs with the uploader's own disclosure — so you can find the mismatches — and with an integrity axis that reads whether a model was injected (a hidden backdoor) or safety-modified.
- 1
- rated 18+ (adult, harmful, or tampered)
- 0
- injection witnessed — a hidden backdoor
- 1
- mismatch — 18+ but not disclosed
- 138
- models assessed
Find
Age rating
138 models shown
| Why | ||||||
|---|---|---|---|---|---|---|
| Qwen2.5-0.5BQwen | — | — | No finding on our coverage | — | 26Mall-time | |
| Llama-3.2-1Bunsloth | — | — | No finding on our coverage | — | 2.1Mall-time | |
| Qwen2.5-0.5B-Instruct-abliteratedhuihui-ai | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | 0.5B | 7.4kall-time | |
| xinnn32/qwen2.5-0.5b-instruct-gensyn-swarm-amphibious_savage_mantis | — | — | No finding on our coverage | — | — | |
| xalphinions/mars-qwen2.5-0.5b-blk8 | — | — | No finding on our coverage | — | — | |
| wuyanzu4692/task-13-qwen-qwen2.5-0.5b-instruct | — | — | No finding on our coverage | — | — | |
| w34423g2/qwen2.5-0.5b-instruct-gensyn-swarm-colorful_ferocious_bear | — | — | No finding on our coverage | — | — | |
| vulcora/gemma-2-2b-it-codealpaca-alignmenttax | — | — | No finding on our coverage | — | — | |
| vagosolutions/sauerkrautlm-gemma-2-2b-it | — | — | No finding on our coverage | — | — | |
| unsloth/qwen2.5-14b-instruct | — | — | No finding on our coverage | — | — | |
| unsloth/qwen2.5-0.5b-instruct | — | — | No finding on our coverage | — | — | |
| unsloth/qwen2.5-0.5b | — | — | No finding on our coverage | — | — | |
| unsloth/meta-llama-3.1-8b-instruct | — | — | No finding on our coverage | — | — | |
| unsloth/meta-llama-3.1-8b | — | — | No finding on our coverage | — | — | |
| unsloth/llama-3.1-8b-instruct | — | — | No finding on our coverage | — | — | |
| unsloth/llama-3-8b-instruct | — | — | No finding on our coverage | — | — | |
| unsloth/llama-3-8b | — | — | No finding on our coverage | — | — | |
| unsloth/gemma-2-9b-it | — | — | No finding on our coverage | — | — | |
| unsloth/gemma-2-2b-it | — | — | No finding on our coverage | — | — | |
| unsloth/gemma-2-2b | — | — | No finding on our coverage | — | — | |
| ukhagani/qwen2.5-0.5b-instruct-gensyn-swarm-yapping_slimy_tarantula | — | — | No finding on our coverage | — | — | |
| toughtty/phi-2 | — | — | No finding on our coverage | — | — | |
| TinyMistral-248M-InstructLocutusque | — | — | No finding on our coverage | 248M | — | |
| TinyMistral-248MLocutusque | — | — | No finding on our coverage | 248M | — | |
| TinyLlama-1.1B-ChatTinyLlama | — | — | No finding on our coverage | 1.1B | — | |
| TinyLlama-1.1B (3T base)TinyLlama | — | — | No finding on our coverage | 1.1B | — | |
| temmy77/qwen2.5-0.5b-instruct-gensyn-swarm-nimble_nasty_falcon | — | — | No finding on our coverage | — | — | |
| susnato/phi-2 | — | — | No finding on our coverage | — | — | |
| suchnost/qwen2.5-0.5b-instruct-gensyn-swarm-clawed_ravenous_gibbon | — | — | No finding on our coverage | — | — | |
| SmolLM3-3B-BaseHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 3B (~3.08B) | — | |
| SmolLM3-3BHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 3B (~3.08B) | — | |
| SmolLM2-360M-InstructHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 360M | — | |
| SmolLM2-360MHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 360M | — | |
| SmolLM2-135M-InstructHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 135M | — | |
| SmolLM2-135MHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 135M | — | |
| SmolLM2-1.7B-Instruct · silent safety-strippublic finetune · lineage undisclosed | Not disclosed — mismatch: the finding the card does not disclose | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Actionable harmful content witnessed | 1.7B | withheld | |
| SmolLM2-1.7B-InstructHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 1.7B | — | |
| SmolLM2-1.7BHugging Face (HuggingFaceTB) | — | — | No finding on our coverage | 1.7B | — | |
| rgerb7363/qwen2.5-0.5b-instruct-gensyn-swarm-plump_scampering_jaguar | — | — | No finding on our coverage | — | — | |
| redhatai/qwen2.5-0.5b-quantized.w8a16 | — | — | No finding on our coverage | — | — | |
| Qwen3-1.7B-BaseAlibaba (Qwen Team) | — | — | No finding on our coverage | 1.7B (~1.72B; ~1.4B non-embedding) | — | |
| Qwen3-1.7B-abliteratedmlabonne (abliteration finetune of Qwen3-1.7B) | — | — | No finding on our coverage | 1.7B (~1.72B; HF file badge rounds to '2B') | — | |
| Qwen3-1.7BAlibaba (Qwen Team) | — | — | No finding on our coverage | 1.7B (~1.72B; ~1.4B non-embedding) | — | |
| Qwen3-0.6B-BaseAlibaba (Qwen Team) | — | — | No finding on our coverage | 0.6B (596M; ~0.44B non-embedding) | — | |
| Qwen3-0.6BAlibaba (Qwen Team) | — | — | No finding on our coverage | 0.6B (596M; ~0.44B non-embedding) | — | |
| Qwen2.5-Math-1.5BAlibaba (Qwen Team) | — | — | No finding on our coverage | 1.5B (~1.54B; card states '1.5B') | — | |
| Qwen2.5-3B-InstructAlibaba (Qwen Team) | — | — | No finding on our coverage | 3B (~3.09B total; ~2.77B non-embedding) | — | |
| Qwen2.5-3BAlibaba (Qwen Team) | — | — | No finding on our coverage | 3B (~3.09B total; ~2.77B non-embedding) | — | |
| Qwen2.5-1.5B-InstructAlibaba (Qwen Team) | — | — | No finding on our coverage | 1.5B (~1.54B total; ~1.31B non-embedding) | — | |
| Qwen2.5-1.5BAlibaba (Qwen Team) | — | — | No finding on our coverage | 1.5B (~1.54B total; ~1.31B non-embedding) | — | |
| Qwen2.5-0.5B-InstructAlibaba (Qwen Team) | — | — | No finding on our coverage | 0.5B (494M; ~0.36B non-embedding) | — | |
| qwen/qwen2.5-32b-instruct | — | — | No finding on our coverage | — | — | |
| qwen/qwen2.5-32b | — | — | No finding on our coverage | — | — | |
| qwen/qwen2.5-14b-instruct-1m | — | — | No finding on our coverage | — | — | |
| qwen/qwen2.5-14b-instruct | — | — | No finding on our coverage | — | — | |
| qwen/qwen2.5-14b | — | — | No finding on our coverage | — | — | |
| qwen/qwen2-0.5b-instruct | — | — | No finding on our coverage | — | — | |
| qwen/qwen2-0.5b | — | — | No finding on our coverage | — | — | |
| Pythia-410MEleutherAI | — | — | No finding on our coverage | 410M (405,334,016 total; ~302M non-embedding) | — | |
| pythia-1b-helpful-sftlomahony (Laura O'Mahony) — finetune of EleutherAI Pythia | — | — | No finding on our coverage | 1B (~1.01B; inherits base size) | — | |
| Pythia-1BEleutherAI | — | — | No finding on our coverage | 1B (1,011,781,632 total; ~806M non-embedding) | — | |
| Pythia-160MEleutherAI | — | — | No finding on our coverage | 160M | — | |
| phi-2-instructvenkycs (finetune of Microsoft Phi-2) | — | — | No finding on our coverage | 2.7B | — | |
| Phi-2Microsoft | — | — | No finding on our coverage | 2.7B | — | |
| Phi-1.5Microsoft | — | — | No finding on our coverage | 1.3B | — | |
| Phi-1_5-Instruct-v0.1rasyosef (finetune of Microsoft Phi-1.5) | — | — | No finding on our coverage | ~1.3B (card benchmark table cites ~1.4B) | — | |
| p2g6gensyn/qwen2.5-0.5b-gensyn-swarm-dappled_yapping_clam | — | — | No finding on our coverage | — | — | |
| ophirparwez/qwen2.5-0.5b-instruct-gensyn-swarm-invisible_mammalian_worm | — | — | No finding on our coverage | — | — | |
| OLMo-2-0425-1B-SFTAllen Institute for AI (Ai2) | — | — | No finding on our coverage | 1B (~1.48B; inherits base size) | — | |
| OLMo-2-0425-1B-InstructAllen Institute for AI (Ai2) | — | — | No finding on our coverage | 1B (~1.48B; inherits base size) | — | |
| OLMo-2-0425-1B-DPOAllen Institute for AI (Ai2) | — | — | No finding on our coverage | 1B (~1.48B; inherits base size) | — | |
| OLMo-2-0425-1BAllen Institute for AI (Ai2) | — | — | No finding on our coverage | 1B (~1.48B total) | — | |
| mrm8488/phi-2-coder | — | — | No finding on our coverage | — | — | |
| mozilla-ai/gemma-2-2b-it-llamafile | — | — | No finding on our coverage | — | — | |
| motocat/qwen2.5-0.5b-instruct-gensyn-swarm-rabid_vigilant_caterpillar | — | — | No finding on our coverage | — | — | |
| mntss/clt-gemma-2-2b-426k | — | — | No finding on our coverage | — | — | |
| mntss/clt-gemma-2-2b-2.5m | — | — | No finding on our coverage | — | — | |
| mlc-ai/qwen2.5-0.5b-instruct-q4f16_1-mlc | — | — | No finding on our coverage | — | — | |
| mlc-ai/phi-2-q4f16_1-mlc | — | — | No finding on our coverage | — | — | |
| mlc-ai/gemma-2-2b-it-q4f16_1-mlc | — | — | No finding on our coverage | — | — | |
| mlabonne/ultrallama-3.1-8b | — | — | No finding on our coverage | — | — | |
| mlabonne/twinllama-3.1-8b-dpo | — | — | No finding on our coverage | — | — | |
| mlabonne/twinllama-3.1-8b | — | — | No finding on our coverage | — | — | |
| mlabonne/numinillama-3.1-8b | — | — | No finding on our coverage | — | — | |
| mlabonne/meta-llama-3.1-8b-instruct-abliterated | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| mlabonne/meta-llama-3-8b | — | — | No finding on our coverage | — | — | |
| mlabonne/hermes-3-llama-3.1-8b-lorablated | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| mlabonne/finellama-3.1-8b | — | — | No finding on our coverage | — | — | |
| mlabonne/datacampllama-3.1-8b | — | — | No finding on our coverage | — | — | |
| mlabonne/chimerallama-3-8b-v3 | — | — | No finding on our coverage | — | — | |
| mlabonne/chimerallama-3-8b-v2 | — | — | No finding on our coverage | — | — | |
| mlabonne/chimerallama-3-8b | — | — | No finding on our coverage | — | — | |
| mkashifali1/qwen2.5-0.5b-instruct-gensyn-swarm-arctic_muscular_heron | — | — | No finding on our coverage | — | — | |
| microsoft/phi-2-pytdml | — | — | No finding on our coverage | — | — | |
| merhabawer/qwen2.5-0.5b-instruct-gensyn-swarm-skittish_shiny_gerbil | — | — | No finding on our coverage | — | — | |
| meowstronot/qwen2.5-0.5b-instruct-gensyn-swarm-patterned_ferocious_ox | — | — | No finding on our coverage | — | — | |
| masha34/qwen2.5-0.5b-instruct-gensyn-swarm-camouflaged_placid_ferret | — | — | No finding on our coverage | — | — | |
| martin2012/qwen2.5-0.5b-instruct-gensyn-swarm-zealous_winged_locust | — | — | No finding on our coverage | — | — | |
| Llama-3.2-1B-InstructMeta (via unsloth ungated mirror) | — | — | No finding on our coverage | 1B (~1.24B) | — | |
| litert-community/qwen2.5-0.5b-instruct | — | — | No finding on our coverage | — | — | |
| kalantar/qwen2.5-0.5b-instruct-gensyn-swarm-leaping_thick_hippo | — | — | No finding on our coverage | — | — | |
| jartine/phi-2-llamafile | — | — | No finding on our coverage | — | — | |
| huihui-ai/qwen2.5-32b-instruct-abliterated | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| huihui-ai/qwen2.5-14b-instruct-abliterated-v2 | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| huihui-ai/qwen2.5-14b-instruct-1m-abliterated | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| huihui-ai/qwen2.5-0.5b-instruct-censortune | — | — | No finding on our coverage | — | — | |
| huihui-ai/qwen2.5-0.5b-instruct-abliterated-v3 | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| huihui-ai/meta-llama-3.1-8b-instruct-abliterated | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| historya/qwen2.5-0.5b-instruct-gensyn-swarm-territorial_mangy_ox | — | — | No finding on our coverage | — | — | |
| grendo55/qwen2.5-0.5b-acelog-sql | — | — | No finding on our coverage | — | — | |
| GPT-2 MediumOpenAI (openai-community) | — | — | No finding on our coverage | 355M | — | |
| GPT-2 · the abstain control— (base model, the control) | — | — | No finding on our coverage | 124M | — | |
| gorkimark/qwen2.5-0.5b-instruct-gensyn-swarm-fluffy_rapid_wildebeest | — | — | No finding on our coverage | — | — | |
| google/gemma-2-2b-jpn-it | — | — | No finding on our coverage | — | — | |
| google/gemma-2-2b-it | — | — | No finding on our coverage | — | — | |
| google/gemma-2-2b | — | — | No finding on our coverage | — | — | |
| google-bert/bert-base-uncased | — | — | No finding on our coverage | — | — | |
| geventy/qwen2.5-0.5b-instruct-gensyn-swarm-skittish_durable_okapi | — | — | No finding on our coverage | — | — | |
| gemma-3-1b-ptGoogle (via unsloth mirror) | — | — | No finding on our coverage | 1B (~1.0B) | — | |
| gemma-2b-itGoogle (via unsloth mirror) | — | — | No finding on our coverage | 2.5B (~2.51B) | — | |
| gemma-2bGoogle (via unsloth mirror) | — | — | No finding on our coverage | 2.5B (~2.51B) | — | |
| furiosa-ai/qwen2.5-0.5b-instruct | — | — | No finding on our coverage | — | — | |
| Falcon3-1B-InstructTII (Technology Innovation Institute) | — | — | No finding on our coverage | 1B (~1.67B; HF file badge rounds to '2B') | — | |
| Falcon3-1B-BaseTII (Technology Innovation Institute) | — | — | No finding on our coverage | 1B (~1.67B) | — | |
| failspy/meta-llama-3-8b-instruct-abliterated-v3 | — | Safety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change | Safety refusals removed (abliteration) | — | — | |
| eleutherai/pythia-70m | — | — | No finding on our coverage | — | — | |
| eleuther-pythia410m-hh-sftlomahony (finetune of EleutherAI Pythia) | — | — | No finding on our coverage | 410M (~405M) | — | |
| efficient-large-model/gemma-2-2b-it | — | — | No finding on our coverage | — | — | |
| e-palmisano/qwen2-0.5b-ita-instruct | — | — | No finding on our coverage | — | — | |
| DialoGPT-smallMicrosoft | — | — | No finding on our coverage | 124M | — | |
| DeepSeek-R1-Distill-Qwen-1.5BDeepSeek-AI | — | — | No finding on our coverage | 1.5B (~1.54B; base Qwen2.5-Math-1.5B; HF file badge rounds to '2B') | — | |
| dania19862017/qwen2.5-0.5b-instruct-gensyn-swarm-unseen_nocturnal_zebra | — | — | No finding on our coverage | — | — | |
| daekeun-ml/phi-2-ko-v0.1 | — | — | No finding on our coverage | — | — | |
| conich/qwen2.5-0.5b-instruct-gensyn-swarm-gregarious_galloping_alpaca | — | — | No finding on our coverage | — | — | |
| chainik08/qwen2.5-0.5b-instruct-gensyn-swarm-fast_whistling_sparrow | — | — | No finding on our coverage | — | — | |
| archivestudio/phi-2 | — | — | No finding on our coverage | — | — | |
| anakin87/gemma-2-2b-neogenesis-ita | — | — | No finding on our coverage | — | — | |
| alamios/deepseek-r1-draft-qwen2.5-0.5b | — | — | No finding on our coverage | — | — |
Protora’s published Phase-0 record — a curated, evidenced set of open models, not all of HuggingFace. The register grows as models are assessed; a model not listed is not yet assessed. See how we rate.