Frozen 16 MB codes replace learned embeddings in small models
A Gemma-shaped ternary model fits in a 46 MB file and runs 615–740 tokens per second on a laptop CPU.
52
AI model
BitNet b1.58
- Mentions · 7d0
- Mentions · 30d1
- All mentions1
- First seenOct 14, 2026
- Last mentioned25d ago
Timeline
1 articles · newest firstAppears with
- llama.cppproduct · 1
- Gemma 3 270Mai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.