MiniCPM-V 4.7 is a 35B vision model that OpenBMB says runs on a phone in 3 GB
OpenBMB's first mixture-of-experts MiniCPM-V is Apache 2.0 and downloadable now. The on-device trick is guessing which experts the next layer will need. Read more >>
Section
Open Weights
Models you can download and run on your own hardware, plus the ones that have been promised but have not shipped. A model counts as downloadable here only once the files are public.
Model tracker
4 models| Model | Maker | Size | Context | License | Weights |
|---|---|---|---|---|---|
| MiniCPM-V 4.7 35B-A3B | OpenBMB | 35B total, about 3B active | Not stated | Apache 2.0 | Downloadable >> |
| Mistral Large 4 | Mistral AI | 1.05T total, 52B active | 1M listed, 524K served | Not announced | Promised |
| Beam | Reflection AI | 501B total, 23B active | 1M (256K during RL training) | Apache 2.0 (promised) | Promised |
| Mellum2.1 Thinking | JetBrains | 12B total, 2.5B active | 131K | Apache 2.0 | Downloadable >> |
Stories
Mistral Large 4 is a trillion-parameter model you cannot download yet
Mistral opened a preview of its 1T-parameter mixture-of-experts model and promised the weights by the end of October. Here is what the numbers say so far. Read more >>
Reflection's Beam bets on fewer tokens, not higher scores
Beam is a 501B-parameter model with Apache 2.0 weights promised this month. Its pitch is not that it wins benchmarks, but that it spends less compute getting close. Read more >>
JetBrains Mellum2.1 is a 12B coding model that learned to use a terminal
The new Mellum is Apache 2.0, downloadable today, and went from 2 percent to 47 percent on SWE-bench Verified in one release. It still trails a smaller Qwen on agent tasks. Read more >>