Last updated: 2026-08-30

Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).

This Qwen3.5-derived model follows the official Qwen3 language list below (119 languages and dialects) and the official Qwen3.5 coverage statement of 201 languages and dialects. Qwen3.5 publishes the expanded coverage count but does not provide an exhaustive 201-name enumeration in its model card. The list below is the complete language list published by Qwen for Qwen3 and is included as the transparent, documented baseline for this derivative.

English, French, Portuguese, German, Romanian, Swedish, Danish, Bulgarian, Russian, Czech, Greek, Ukrainian, Spanish, Dutch, Slovak, Croatian, Polish, Lithuanian, Norwegian Bokmål, Norwegian Nynorsk, Persian, Slovenian, Gujarati, Latvian, Italian, Occitan, Nepali, Marathi, Belarusian, Serbian, Luxembourgish, Venetian, Assamese, Welsh, Silesian, Asturian, Chhattisgarhi, Awadhi, Maithili, Bhojpuri, Sindhi, Irish, Faroese, Hindi, Punjabi, Bengali, Oriya, Tajik, Eastern Yiddish, Lombard, Ligurian, Sicilian, Friulian, Sardinian, Galician, Catalan, Icelandic, Tosk Albanian, Limburgish, Dari, Afrikaans, Macedonian, Sinhala, Urdu, Magahi, Bosnian, Armenian; Chinese (Simplified Chinese, Traditional Chinese, Cantonese), Burmese; Arabic (Standard, Najdi, Levantine, Egyptian, Moroccan, Mesopotamian, Ta’izzi-Adeni, Tunisian), Hebrew, Maltese; Indonesian, Malay, Tagalog, Cebuano, Javanese, Sundanese, Minangkabau, Balinese, Banjar, Pangasinan, Iloko, Waray (Philippines); Tamil, Telugu, Kannada, Malayalam; Turkish, North Azerbaijani, Northern Uzbek, Kazakh, Bashkir, Tatar; Thai, Lao; Finnish, Estonian, Hungarian; Vietnamese, Khmer; Japanese, Korean, Georgian, Basque, Haitian, Papiamento, Kabuverdianu, Tok Pisin, Swahili.

Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).

Role: Dedicated translator (9B). Think-model — for deterministic translation use a closed-think prefill (<think>\n\n</think>\n\n after assistant\n) to suppress reasoning, otherwise it emits a reasoning trace instead of the translation. BF16 = PRIMARY. Sibling: -GGUF-Q4_K_M.gguf (5.24 GB, fits 6GB GPU).

Positioning: In the published FLORES-200 comparison below, this model is the best-performing pure translator among the tested open-source baselines by average COMET (0.8870), chrF++ (50.7), and BLEU (22.5). This benchmark is a limited internal comparison and does not establish that it is the best open-source translation model in the world.

Sample (eng→rus): «Теперь у нас есть мыши в возрасте четырёх месяцев, которые ранее страдали диабетом, но сейчас не болеют им», — добавил он.

Best pure translator (marginal: +2.1 chrF++ over the 4B, BLEU tied) but NOT a supervisor. Use 9B for the final translation pass when VRAM allows; the 4B-LongCtx is the all-rounder.

⚠️ n=20 quick estimate (partly within noise). Eval on GPU via llama-completion.exe -ngl 99. Written: 2026-06-17

Real eval (not smoke): n=100 × 4 directions (eng↔rus, eng↔cmn), GPU via resident llama-server -ngl 99. Primary metric COMET (wmt22-comet-da, neural — how "best translator" is judged), plus chrF++ / BLEU / length-ratio. Each model prompted in its own native format (MT2 = dubbing ChatML "SOURCE (lang): … Только перевод"; 9B = ChatML + no-think). Data + COMET checkpoint: D:/models/by_expert/07_MT_TRANSLATION.

Per-direction COMET — 9B-Translate wins all 4 (eng-rus .902 / eng-cmn .897 / rus-eng .872 / cmn-eng .877); MT2-7.5B 2nd, MT2-1.8B 3rd.