PR
PrismML
Multimodal model ·Jul 2026

Bonsai 27B

Multimodal Open Source
27B
Parameters
262K
Context

About Bonsai 27B

Bonsai 27B is an AI model developed by PrismML, in the multimodal category, released in 2026, made available as an open-source model with 27B params. PrismML's Bonsai 27B is an extreme quantization of Qwen 3.6 27B: a 1-bit build at 3.9GB retaining ~90% quality and a ternary build at 5.9GB retaining ~95%. Small enough for phone deployment while staying multimodal with full 262K context.

On this page you'll find Bonsai 27B's full specifications, including a context window of 262K tokens. Review provider pricing and benchmark scores below, or compare Bonsai 27B head-to-head with other multimodal models.

Run Bonsai 27B locally — what to buy

Share this build ↗

Sized to what Bonsai 27B actually needs (~262k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Software support

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run Bonsai 27B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Bonsai 27B

Frequently asked questions

What is Bonsai 27B?

PrismML's Bonsai 27B is an extreme quantization of Qwen 3.6 27B: a 1-bit build at 3.9GB retaining ~90% quality and a ternary build at 5.9GB retaining ~95%. Small enough for phone deployment while staying multimodal with full 262K context. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Bonsai 27B?

Bonsai 27B was developed by PrismML and released in 2026.

Is Bonsai 27B open source or proprietary?

Bonsai 27B is released as open source — its weights are publicly available to download, run locally and fine-tune.

What is Bonsai 27B's context window?

Bonsai 27B supports a context window of 262K tokens, and has 27B params.

How much does Bonsai 27B cost?

Pricing for Bonsai 27B depends on the provider. See the providers table on this page for the latest API rates.

How does Bonsai 27B perform on benchmarks?

Benchmark scores for Bonsai 27B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

Ternary Bonsai 27B benchmarked and tested vs Qwen 27B - 16GB Local LLM setup
[FAST AI NEWS] Ternary Bonsai 27B
Bonsai 27B Deep Dive – 1-Bit, Ternary & Full Precision Compared!
Bonsai 27B — The First 27B AI Model That Runs on Your Phone

Know a great video about Bonsai 27B?