Bonsai 27B — local AI model by PrismML
Written by Jakub Rusinowski · Last updated
PREVIEW (July 2026). The first 27B-class model that runs on a phone. Bonsai 27B is PrismML's extreme low-bit rebuild of Qwen3.6-27B: the architecture is unchanged, but the weights are squeezed to roughly 1–1.7 bits each. The 1-bit build is just 3.9 GB — small enough for an iPhone — while the ternary build is 5.9 GB and aimed at laptops. Both are multimodal (text + images), carry a 262K-token context, and ship under Apache 2.0. PrismML reports the ternary build keeps more than 95% of the full-precision (FP16) baseline across a 15-benchmark suite and the 1-bit build more than 90%, running about 11 tok/s on an iPhone 17 Pro. Specs are from launch coverage — verify against the Hugging Face model cards.
Variants
The smallest Bonsai 27B variant needs about 5 GB of VRAM at 1-bit (binary, ~1.125 bpw) — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| 1-bit Bonsai 27B → 27B | ~4.6 GB | 262,144 | ollama run bonsai-27b | |
| Ternary Bonsai 27B → 27B | ~6.6 GB | 262,144 | ollama run bonsai-27b |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Bonsai 27B locally
Install Ollama, then pull the tag.
ollama run bonsai-27bPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: 1-bit Bonsai 27B, Ternary Bonsai 27BRecommended GPU
The cheapest catalogued GPU that runs Bonsai 27B locally (min 5 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run Bonsai 27B on my GPU?
- Bonsai 27B on AMD Radeon RX 9060 XT 8GB
- Bonsai 27B on Intel Arc B570
- Bonsai 27B on Intel Arc B580
- Bonsai 27B on NVIDIA GeForce RTX 3060 (12GB)
- Bonsai 27B on NVIDIA GeForce RTX 3070
- Bonsai 27B on NVIDIA GeForce RTX 3070 Ti
- Bonsai 27B on NVIDIA GeForce RTX 3080 (10GB)
- Bonsai 27B on NVIDIA GeForce RTX 4060
- Bonsai 27B on NVIDIA GeForce RTX 4070
- Bonsai 27B on NVIDIA GeForce RTX 4070 Super
- Bonsai 27B on NVIDIA GeForce RTX 4070 Ti
- Bonsai 27B on NVIDIA GeForce RTX 5060
- Bonsai 27B on NVIDIA GeForce RTX 5060 Ti 8GB
- Bonsai 27B on NVIDIA GeForce RTX 5070
Bonsai 27B — frequently asked questions
How much VRAM does Bonsai 27B need?
Bonsai 27B needs about 5 GB VRAM at 1-bit (binary, ~1.125 bpw) quantization for its smallest variant. Variants: 1-bit Bonsai 27B (5 GB, 1-bit (binary, ~1.125 bpw)); Ternary Bonsai 27B (7 GB, Ternary (1.58-bit, ~1.71 bpw)). On Apple Silicon, unified memory counts toward this requirement.
Can I run Bonsai 27B on an RTX 4090 (24 GB)?
Yes — Bonsai 27B 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 1-bit (binary, ~1.125 bpw).
What quantization should I use for Bonsai 27B?
Bonsai 27B 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 (1-bit (binary, ~1.125 bpw)). Use the vendor's runtime for that format, as the variant pages describe.
How do I run Bonsai 27B with Ollama?
Bonsai 27B 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.