Model · language model
JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP
JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP is a language model from JetBrains, first covered on 2 November 2026. It is available as open weights you can download and run (licence: Apache 2.0). Its context window is 131,072 tokens.
Last updated
Quick facts
- Who makes JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP?
- JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP is made by JetBrains. JetBrains news →
- When was JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP released?
- The first report of JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP's release that Digest AI covered was published on 2 November 2026. JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP · Hugging Face →
- What type of model is JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP?
- JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP is a language model.
- Are JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP's weights open?
- Yes. JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP is released as open weights that can be downloaded and run, under the Apache 2.0 licence.
- What is JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP's context window?
- JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP's context window is 131,072 tokens.
- Where is JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP available?
- JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP is available as open weights that can be downloaded and run.
Taken from the coverage, not from our own testing. A question is left out when none of the reports we read gave the answer. All tracked models →
1 story about JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP
-
JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP · Hugging Face
The 12 B mixture‑of‑experts model keeps the same architecture as the previous version—28 layers, 2.5 B active parameters, 64 experts (8 active per token), 131,072 token context length, and a 1,024‑token sliding…
1 source primary sourcehuggingface.co
