Text / LLM
MemT-1.0-Nano
MemT-1.0-Nano by MemTensor has no tracked price. It has no overseas route listed on this record. Last checked 2026-10-31.
MemTensor · apache-2.0 · 36B
—
MoE memory model on a Qwen3.6-35B-A3B backbone. Model card: 36B total, 3B activated. HF safetensors count is 35.1B. config.json max_position_embeddings is 262144; the card does not state a context window. Card license is Apache-2.0. release_date is the Hugging Face repo creation date. No USD price.
How to use it from outside China
- Weights are public. Download them from Hugging Face. https://huggingface.co/MemTensor/MemT-1.0-Nano
- This record does not list an official international API, OpenRouter, or another overseas host.
- Confirm the price on the source before you rely on it. Checked 2026-10-31. Pricing source
Usable outside China?
No official international API listed.
Not listed on OpenRouter.
Questions
Can I use MemT-1.0-Nano from outside China?
Unknown — not on the record yet
How much does MemT-1.0-Nano cost per 1M tokens?
Unknown — not on the record yet
Is the MemT-1.0-Nano API OpenAI-compatible?
Unknown — not on the record yet
Are MemT-1.0-Nano weights open, and under which license?
Yes. License: apache-2.0.
Sources
Related models
More from MemTensor
Other text models
Compare MemT-1.0-Nano with MemT-1.0-Flash · More text · MemTensor
Weekly brief
Get the weekly brief on Chinese AI models you can use outside China. Free.