Testing PrismML Bonsai 2

PrismML released Bonsai 2 27B, a ternary-weight compression of Qwen3.8 27B that cuts model size from about 56 GB to 5.9 GB while retaining roughly 98% of the original model's benchmark score. In a hands-on test on an M4 Mac with 24 GB of RAM, the model ran a code review through a Pi coding agent in 30 minutes at about 40 tokens per second, following the tester's codereview.md rules. Bonsai 2 runs on Mac via Metal, on Linux and Windows via CUDA, Vulkan, and ROCm, or on CPU alone.

Testing PrismML Bonsai 2 PrismML released Bonsai 2 27B this week. It is built on Qwen3.8 27B, but compressed to ternary weights: each weight is +1, 0, or -1 instead of 16 bits. That drops the size from about 56 GB to 5.9 GB. On PrismML’s benchmark suite, it keeps about 98% of the original model’s score. It runs on a Mac Metal , on Linux or Windows CUDA, Vulkan, ROCm , or on CPU alone. I tested it on my M4 Mac with 24 GB of RAM. I wired it to my Pi coding agent and gave it a code review task. It is pretty cool. Bonsai 2 followed my codereview.md rules. It checked the change against the other files in the repo, the way I asked it to. The full task took 30 minutes. Token speed was about 40 tokens per second, not slow at all. A 27B model that fits in 6 GB and still runs a real code review on a laptop is a good sign for local coding agents.