Bonsai 27B

Released
2026-07-14
Last refreshed
2026-10-22
Status
Researched today
Open sourceCommercial use: permittedMultimodalRAGAgentsLong contextVisionJSON / Tool useMultimodalAgents

Bonsai 27B is available now for rag, agents, and long context with open-source and 256K context; evaluate it while provider pricing coverage matures.

PrismML releases · 14 in the last 12 monthsChangelog →
Specifications
Family
Bonsai
Released
2026-07-14
Context
256K
Parameters
27.36B
Specialization
on-device
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

PrismML (Prism ML, Inc.) builds ultra-dense 1-bit and ternary Bonsai models for on-device and efficient datacenter infer

Website
Pricing

No tracked provider pricing is available yet.

About

1-bit Bonsai 27B is PrismML's footprint-oriented 27B model from the July 2026 Bonsai 27B launch: Qwen3.6 27B compressed to binary weights at 1.125 effective bits per weight, about 3.9 GB, small enough for an iPhone 17 Pro. PrismML reports it keeps about 90% of full-precision performance across 15 thinking-mode benchmarks, with reasoning, tool calling and optional image input; 262K-token context. Sibling of Ternary Bonsai 27B. Apache 2.0.

Providers

No active provider routes are tracked for this model yet.

Capabilities

VisionMultimodalReasoningJSON / Tool use

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

bonsai-27bprism-ml/Bonsai-27B-ggufprism-ml/Bonsai-27B-mlx-1bit1-bit Bonsai 27B