Videos
4 total
| Thumb | Title | Channel | Status | Published |
|---|---|---|---|---|
|
The Local Coding Breakthrough We Waited For? (Bonsai 2)
Bonsai 2 compresses Qwen 3.8 from 54GB to 5.9GB using ternary quantization (1.76 bits per weight), claiming 98%... |
Cloud Codes | summarized | 2026-09-19 04:30 |
|
Bonsai 2 27B and Hermes Agentic Coding Local Ai Test vs Qwen 3.8 27B fp16
Bonsai 2 27B's ternary quantization claims 98% quality retention at 9x smaller size, but in practice the quality... |
Digital Spaceport | summarized | 2026-09-18 16:40 |
|
Bonsai 2 27B First Test – Is THIS the BEST Single-GPU AI Model?
Prism ML's Bonsai 2 27B is a heavily quantized version of Qwen 3.8 27B that fits on a single GPU with 12-16 GB VRAM,... |
Bijan Bowen | summarized | 2026-09-18 04:50 |
|
Bonsai 27B Deep Dive – 1-Bit, Ternary & Full Precision Compared!
Prism ML's Bonsai 27B models (ternary and 1-bit) dramatically shrink a Qwen 3.6 27B base while retaining surprising... |
Bijan Bowen | summarized | 2026-07-16 14:12 |
Frontier News · by Hyperjump Technology