A small language model that runs on a CPU at about 2,000 tokens a second in 40 MB of RAM, with no network and no
1
18 commits
1 linked in READMEs
updated Sep 14, 2026
README
SHADOW 50M Instruct
44M parameters · ternary · exact circuits inside the model · 100M-token archive on disk · 19.8 MB · CPU, offline
A small language model that runs on a CPU at about 2,000 tokens a second in 40 MB of RAM, with no network and no framework. It computes arithmetic, dates, units, counting and sorting with circuits inside its weights, and it keeps records on disk as its own memory, quoting the record it read. Built from scratch; the weights are ternary and the vocabulary table is frozen.
The full technical read, the kernels for Windows and Linux, the browser page, the harnesses and every measurement are on GitHub: github.com/QLNI/SHADOW-50M-Instruct. Please start there.
Downloads
| file | what it is | size |
|---|---|---|
| shadow50_instruct.shdw | the deployment container, version 1.1: ternary weights, the frozen vocabulary table, runtime constants, the self-test prompt. Drop it into deployment/ of the GitHub repository and run python shadow_chat.py. | 19.8 MB |
| shadow50_instruct.pt | the master weights, for fine-tuning with the kit in the repository (finetune/). | 310 MB |
Try it in your browser
qlni.github.io/SHADOW-50M-Instruct/web: the same kernel compiled to WebAssembly, the 19.8 MB model fetched once, nothing installed.
Licence
MIT. If it turns out useful, a mention of SHADOW somewhere in your work would be appreciated.
© QLNI 2026
Contributors
18 commits
Similar repos
A small language model that runs on a CPU at about 2,000 tokens a second in 40 MB of RAM, with no network and no
1
18 commits
1 linked in READMEs
updated Sep 14, 2026
README
SHADOW 50M Instruct
44M parameters · ternary · exact circuits inside the model · 100M-token archive on disk · 19.8 MB · CPU, offline
A small language model that runs on a CPU at about 2,000 tokens a second in 40 MB of RAM, with no network and no framework. It computes arithmetic, dates, units, counting and sorting with circuits inside its weights, and it keeps records on disk as its own memory, quoting the record it read. Built from scratch; the weights are ternary and the vocabulary table is frozen.
The full technical read, the kernels for Windows and Linux, the browser page, the harnesses and every measurement are on GitHub: github.com/QLNI/SHADOW-50M-Instruct. Please start there.
Downloads
| file | what it is | size |
|---|---|---|
| shadow50_instruct.shdw | the deployment container, version 1.1: ternary weights, the frozen vocabulary table, runtime constants, the self-test prompt. Drop it into deployment/ of the GitHub repository and run python shadow_chat.py. | 19.8 MB |
| shadow50_instruct.pt | the master weights, for fine-tuning with the kit in the repository (finetune/). | 310 MB |
Try it in your browser
qlni.github.io/SHADOW-50M-Instruct/web: the same kernel compiled to WebAssembly, the 19.8 MB model fetched once, nothing installed.
Licence
MIT. If it turns out useful, a mention of SHADOW somewhere in your work would be appreciated.
© QLNI 2026
Similar repos
Linked in READMEs
Contributors
18 commits