Verified open translation models that fit in 24 GB on RTX 3090 24GB, smallest first — with license clarity and hosted-download status. Top pick: Helsinki-NLP/opus-mt-en-sw (~1.87 GB).
Hugging Bay is intentionally crawlable for search engines, answer engines, user-requested AI fetches, frontier AI assistants, and open-source agents. Public pages describe verified open-source AI artifact metadata, provenance, licenses, community trust signals, and selective hosted mirrors with hashes. Hugging Bay does not bypass gated or restricted upstream access controls.
Machine-readable entrypoints: robots.txt, AI search guidance, well-known AI search JSON, AI citation packs, well-known AI citation JSON, llms.txt, llms-full.txt, AI crawler policy, AI bot allowlist, answer-engine manifest, agent manifest, OpenAPI, and indexing status.
Verified open translation models that fit in 24 GB on RTX 3090 24GB, smallest first — with license clarity and hosted-download status. Top pick: Helsinki-NLP/opus-mt-en-sw (~1.87 GB).
| # | Model | Est. VRAM | License | Commercial | Hosting | Fit page |
|---|---|---|---|---|---|---|
| 1 | Helsinki-NLP/opus-mt-en-sw | ~1.87 GB | apache-2.0 | yes | external | check |
| 2 | mdpead/en-cy-translation | ~1.87 GB | cc-by-4.0 | yes | external | check |
| 3 | aman4014/whisper-bil-model-100k-ct2-int8_float16 | ~1.87 GB | mit | yes | external | check |
| 4 | MihaiPopa-1/OmniTranslate-1.1 | ~1.87 GB | apache-2.0 | yes | external | check |
| 5 | telecomadm1145/mamba2_ja2zh_zh2ja_trans | ~1.87 GB | mit | yes | external | check |
| 6 | mujtabaumarr/opus-mt-en-ur-vocational | ~1.87 GB | apache-2.0 | yes | external | check |
| 7 | Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat | ~1.87 GB | apache-2.0 | yes | external | check |
| 8 | dsfsi/tiny_aya_earth-lora-r4-eng-nso | ~1.87 GB | apache-2.0 | yes | external | check |
| 9 | Helsinki-NLP/opus-mt-tc-big-en-fi | ~1.87 GB | cc-by-4.0 | yes | external | check |
| 10 | Helsinki-NLP/opus-mt-ml-en | ~1.87 GB | apache-2.0 | yes | external | check |
Other GPUs: RTX 4090 24GB · RTX 3060 12GB · NVIDIA T4 16GB (free Colab) · A100 80GB · H100 80GB · mac-m3-max-64
Other tasks on RTX 3090 24GB: coding · chat · reasoning · summarization · vision · audio · rag · agents
Fit = weights + KV-cache estimate under 24 GB. Recomputed hourly from live catalog state.