MemT-1.0-Nano
MemT-1.0-Nano is available now for general LLM work with open-source; evaluate it while provider pricing coverage matures.
- Family
- MemT 1.0
- Released
- 2026-10-20
- Parameters
- 36B (3B activated)
- Architecture
- Mixture of Experts
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
No tracked provider pricing is available yet.
About
MemT-1.0-Nano is MemTensor's smaller memory-native language model, built on Qwen3.6-35B-A3B with 36B total and 3B activated parameters. A native memory block runs alongside the backbone's attention and folds past turns into a fixed-size memory state (451M trainable memory parameters, 10M dynamic state) that can be saved and restored, so later turns reuse history without reloading the original text. MemTensor reports about 66 times less storage than a full-context KV cache at 128K history. Open weights under Apache 2.0.
Providers
No active provider routes are tracked for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
MemTensor/MemT-1.0-NanoMemT 1.0 NanoNo tracked provider pricing is available yet.