Ternary Bonsai 2 — local AI model by PrismML
Written by Jakub Rusinowski · Last updated
PrismML's second ternary family: four vision-language models whose weights are only −1, 0 or +1, stored in packed formats about nine times smaller than FP16. The 2B, 4B and 9B are rebuilt from Qwen3.5 and the 27B from Qwen3.8-27B, so all four keep a 262,144-token context and a hybrid attention backbone (three linear-attention layers to every full-attention layer), which also keeps the KV cache small. They ship ONLY in these packings — there is no Q4_K_M or Q8_0 build — and the smallest files need PrismML's own llama.cpp fork or mlx-vlm to load. Apache 2.0. The 27B succeeds the July Bonsai 27B, which was built on Qwen3.6.
Variants
The smallest Ternary Bonsai 2 variant needs about 1 GB of VRAM at PTQ1_0 ternary — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Ternary Bonsai 2 2B → 2B | ~1.2 GB | 262,144 | cloud-hosted tag | |
| Ternary Bonsai 2 4B → 4B | ~1.8 GB | 262,144 | cloud-hosted tag | |
| Ternary Bonsai 2 9B → 9B | ~2.8 GB | 262,144 | cloud-hosted tag | |
| Ternary Bonsai 2 27B → 27B | ~6.7 GB | 262,144 | cloud-hosted tag |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Ternary Bonsai 2 locally
Install Ollama, then pull the tag.
No Ollama library entry. The packed ternary formats need PrismML's llama.cpp fork (or upstream llama.cpp for the Q2_0 file only); on Apple devices use the MLX build with mlx-vlm 0.7.8 or newer.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Ternary Bonsai 2 2B, Ternary Bonsai 2 4B, Ternary Bonsai 2 9B, Ternary Bonsai 2 27BRecommended GPU
The cheapest catalogued GPU that runs Ternary Bonsai 2 locally (min 1 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run Ternary Bonsai 2 on my GPU?
Ternary Bonsai 2 — frequently asked questions
How much VRAM does Ternary Bonsai 2 need?
Ternary Bonsai 2 needs about 1 GB VRAM at PTQ1_0 ternary quantization for its smallest variant. Variants: Ternary Bonsai 2 2B (1 GB, PTQ1_0 ternary); Ternary Bonsai 2 4B (2 GB, PTQ1_0 ternary); Ternary Bonsai 2 9B (3 GB, PTQ1_0 ternary); Ternary Bonsai 2 27B (7 GB, PTQ1_0 ternary). On Apple Silicon, unified memory counts toward this requirement.
Can I run Ternary Bonsai 2 on an RTX 4090 (24 GB)?
Yes — Ternary Bonsai 2 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at PTQ1_0 ternary.
What quantization should I use for Ternary Bonsai 2?
Ternary Bonsai 2 is published only pre-quantised, so there is no Q4_K_M or Q8_0 build to choose between: each variant ships in the format listed beside it above (PTQ1_0 ternary). Use the vendor's runtime for that format, as the variant pages describe.
How do I run Ternary Bonsai 2 with Ollama?
Ternary Bonsai 2 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.