ForgePlex-M2.1-10M
ForgePlex-M2.1-10M is a 9.99-million-parameter decoder-only language model with a 1,024-token context. Its architecture includes GQA, RoPE, RMSNorm, SwiGLU, attention output gates, and refresh gates.
What it does
A person can download the model and use it to generate text from prompts.
- Availability
- Model repository and usage instructions are published on Hugging Face.
- Pricing model
- Not established
- Deployment
- Usage instructions show loading the model locally with Transformers.
- Privacy
- Not established
- Licence
- Apache-2.0
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
5 claims- The model is published at Hugging Face under ForgeWorks/ForgePlex-M2.1-10M. [1]
- The model is a 9.99-million-parameter decoder-only language model. [1]
**ForgePlex-M2.1-10M** is a 9.99M-parameter decoder-only language model from ForgeWorks, trained on 40b tokens.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model was trained on 40 billion tokens. [1]
**ForgePlex-M2.1-10M** is a 9.99M-parameter decoder-only language model from ForgeWorks, trained on 40b tokens.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The usage example loads the model locally using Transformers.
- The model is licensed under Apache-2.0. [1]
This is the most complete model we've built so far.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/ForgeWorks/ForgePlex-M2.1-10M
Retrieved 2026-10-29 00:21 UTC
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-13 19:06 UTC | material change | availability, deployment | Current |
| 2 | 2026-10-11 20:58 UTC | material change | access, pricing, availability, deployment | Current |
| 1 | 2026-10-10 21:52 UTC | publication | None | Current |
In briefs
1- Two local models can classify, route, or score text and images Daily brief 2026-10-10
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.