PrismML Releases Ternary Bonsai 2 27B: A 5.9 GB Apache 2.0 Model Retaining 98.2% of Qwen3.8 27B Performance
PrismML released Ternary Bonsai 2 27B, a 5.93 GB Apache 2.0 ternary-weight model retaining 98.2% of Qwen3.8 27B's benchmark performance.
58
Product
Qwen3.8 27B
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 17, 2026
- Last mentionedSep 18, 2026
Timeline
2 articles · newest firstPrismML hopes its tiny LLM will change how we all use AI
PrismML released Bonsai 2 27B, compressing Alibaba's Qwen 27B to 5.9 GB with ternary weights while retaining 98% of benchmark performance.
48
Appears with
- Qwen3.8 27Bai model · 2
- PrismMLvendor · 2
- Khosla Venturesorganization · 1
- Databricksorganization · 1
- Caltechorganization · 1
- Qwenvendor · 1
- Bonsai 2 27Bproduct · 1
- Ternary Bonsai 2 27Bproduct · 1
- Appleorganization · 1
- Cerberus Capitalorganization · 1
- Bonsai 2 27Bai model · 1
- MLXproduct · 1
- Ternary Bonsai 2 27Bai model · 1
- PrismMLorganization · 1
- llama.cppproduct · 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.