Still supported but not recommended for new installs.
Qwen 3 MoE models need more bits in quantisation, try keep to q8 or above for MoE models.
Qwen 3 Dense models still functions with acceptable quality at quantisations down to q4.
The recent Qwen2.5 release has pushed open source large language models (LLMs) to new heights, beating the previous open source leader Llama 3.1 across a number of benchmarks.
Qwen-2.5-7B-Q4 model is now available by default (along with Llama-3.1-8B-Q4 model) on most public Compute Asset e,g. model.aunsw.88.io
For Compute Assets with 16GB+ of VRAM on GPUs, running Qwen2.5-14B-Q8 model is recommended.
Becareful that the 3B and 72B variants of Qwen 2.5 ave some restrictions on commercial use, the others licensed under Apache 2.0 which is ok for most type of use.
For those with low-end GPUs:
Ollama - qwen2.5-14b (9GB)
Notes:
Recommended:
Ollama - qwq-32b (20GB)
Qwen 3 is a hybrid model, so it can operate in either /think or /no_think mode. Qwen 3 also has Dense models and MoE (mixture of experts) models.
32b is the top dense model available.
41GB. 79%GPU 21%CPU
14b is the recommended Dense model for most use cases.
15GB 100%GPU
30b is the a small MoE model.
27GB 100%GPU
For the 26.02 release the Advanced Vision Model is Qwen2.5-VL-72B-Instruct-4bit.
Qwen3-VL supports text, images, videos and agents
Qwen3-vl vision transformers (ViTs) employs full self-attention, whereas Qwen2.5-VL's ViTs primarily uses the more efficient window-based attention.
Joint pretraining on text and images teaches the model deeper relationships between concepts, boosting its language skills beyond what a text-only model learns.
Features a massive 256K-token context window for both text and interleaved inputs.
Supports 119 languages and dialects (32 of them have OCR ability).
| Language Family | Languages & Dialects |
|---|---|
| Indo-European | 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 |
| Sino-Tibetan | Chinese (Simplified Chinese, Traditional Chinese, Cantonese), Burmese |
| Afro-Asiatic | Arabic (Standard, Najdi, Levantine, Egyptian, Moroccan, Mesopotamian, Ta’izzi-Adeni, Tunisian), Hebrew, Maltese |
| Austronesian | Indonesian, Malay, Tagalog, Cebuano, Javanese, Sundanese, Minangkabau, Balinese, Banjar, Pangasinan, Iloko, Waray (Philippines) |
| Dravidian | Tamil, Telugu, Kannada, Malayalam |
| Turkic | Turkish, North Azerbaijani, Northern Uzbek, Kazakh, Bashkir, Tatar |
| Tai-Kadai | Thai, Lao |
| Uralic | Finnish, Estonian, Hungarian |
| Austroasiatic | Vietnamese, Khmer |
| Other | Japanese, Korean, Georgian, Basque, Haitian, Papiamento, Kabuverdianu, Tok Pisin, Swahili |
