PrismML Open-Sources Ternary Bonsai 2 Models: 2B at Just 0.43GB

PrismML has released Bonsai 2, an open-source ternary model family available in 2B, 4B, and 9B sizes with file sizes of just 0.43GB, 0.95GB, and 2.0GB respectively. Trained on Qwen3.5, the models target local execution on everyday devices such as phones, PCs, and wearables. The family is live on Hugging Face as the Bonsai 2 Small collection, offering GGUF and MLX 2bit quantized versions that run on WebGPU.

Confirmed

• Model specs: 2B (0.43GB), 4B (0.95GB), 9B (2.0GB), based on Qwen3.5, open weights
• Emphasis on reasoning, visual understanding, and tool-calling capabilities; according to shared posts, instruction-following actually outperforms Qwen3.5
• Available on Hugging Face, including GGUF and MLX 2bit quantized versions, with WebGPU support
• Design philosophy: as @cephaloform relayed HessianFree's summary, on-device models should focus on following instructions, calling the right tools, and staying concise, rather than pushing the ceiling of raw intelligence

Why it matters

Ternary quantization compresses a 9B model to under 2GB, making it realistic to run fairly large models locally on consumer devices like mid-range phones—a representative advance for on-device AI adoption.

2026-10-16 ~ 2026-10-16 · 7 related posts

• [source] Ternary Bonsai 2 (2B/4B/9B) released: 2B runs in-browser at 500 tok/s on M4 Max — xenovatech · 2026-10-16
• Bonsai 2's philosophy: phone models just need to follow orders, call tools, and stop rambling — cephaloform · 2026-10-16
• PrismML ships Bonsai 2 ternary models: 9B fits in 2GB and beats Qwen3.5 on instruction following — calabi_and_yau · 2026-10-16
• [source] Bonsai 2 Small multimodal models hit HF with 2-bit MLX builds and WebGPU demo — cephaloform · 2026-10-16

3 near-duplicate retellings: gajesh · gajesh · victormustar