tern-tc-100m is an open-weight model from Playra, released under Apache License 2.0. Its published files total 402.7 MB.
A 100M-parameter ternary code model (BitNet b1.58 linears), trained on 10B tokens next to a full-precision twin, with the twin's scores beside it -- the ternary model is the weaker of the two. The ternary model is weaker than its full-precision twin.
Model Card
By Playra, published under apache-2.0, revision d6ffb6062137.
A 100M-parameter ternary code model (BitNet b1.58 linears), trained on 10B tokens next to a full-precision twin, with the twin's scores beside it -- the ternary model is the weaker of the two. The ternary model is weaker than its full-precision twin. This is a research checkpoint, not a coding assistant. Every fact and every number about this model lives in modelcard.t27 in this repository, and nowhere else: it is a t27 module that is compiled and tested by t27c. This README states none of them. The checkpoint is final.pt, loaded with the model.py next to it, using tokenizer.json.
Read Playra's full model card
A 100M-parameter ternary code model (BitNet b1.58 linears), trained on 10B tokens next to a full-precision twin, with the twin's scores beside it -- the ternary model is the weaker of the two.
The ternary model is weaker than its full-precision twin. This is a research checkpoint, not a coding assistant.
Every fact and every number about this model lives in model_card.t27 in this repository, and nowhere else: it is a t27 module that is compiled and tested by t27c. This README states none of them. The checkpoint is final.pt, loaded with the model.py next to it, using tokenizer.json.
Identity and Version
- Repository
- playra/tern-tc-100m
- Publisher
- Playra
- Task
- Not stated by the source
- Modality
- Other
- Library
- pytorch
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- d6ffb6062137b54ac4491b204af7afd26e2e64ce
- First published
- 2026-10-18
- Last updated
- 2026-10-18
Files and Weights
9 files, 402.7 MB in total. The weights are 1 file totalling 400.4 MB in pt.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| final.pt | Weights | 400.4 MB | 620c80b642ff |
| model.py | Configuration | 17.6 KB | — |
| runs/fp100m_pair/summary.json | Configuration | 2.9 KB | — |
| runs/tern100m_pair/summary.json | Configuration | 2.9 KB | — |
| LICENSE | Documentation | 11.4 KB | — |
| README.md | Documentation | 756 B | — |
| model_card.t27 | Other | 22.3 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 2.2 MB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 400.4 MB
Released by Playra through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 400.4 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About tern-tc-100m
Can I use tern-tc-100m commercially?
Yes. tern-tc-100m is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.