Every open model ships frozen.
What if it could learn and update its own weights as it's being used?
I have been working on a bit of engineering called Living Weights for about three months, and I think it's time to release it.
The model becomes uniquely yours, no KV stashing, no MD files, no trickery.... just live learning. 😎
Unload the model, move it to another machine, and it still knows what you told it. Could this be the start of recursive self improvement for local AI?
It drops in the latest TensorFold release today, with support for @NVIDIAAI Nemotron Lightning. 🤯👀
@abheer@sundeep@NaderLikeLadder
Special thanks to @volatilemarkts for the name.
Time for some love for single DGX Spark owners.
Qwen3.8 Flash Next on TensorFold v1.0 is out ✨
- Runs on TensorFold Zig.
- Swapped the MLX quant for Int4-AutoRound.
- Much more reliable than before.
- Squashed many bugs.
Performance:
- 64.4 tok/s on prose, single stream
- 140 tok/s on prose, 4 concurrent streams
- 200 tok/s on prose, 8 concurrent streams
- Prefill ~2500-2600 tok/s.
Still the best model you can run on a single DGX Spark. Nothing else comes close. @ashxhart
Get it here:
https://t.co/DZy94NF7zm