PrismML Releases Bonsai 2 27B Multimodal Model

Sep 17, 2026
PrismML released Bonsai 2 27B, a compressed multimodal model that requires 5.9 GB of memory and runs on consumer hardware.

PrismML announced in a press release the release of Bonsai 2 27B, a ternary multimodal model based on Qwen3.8 27B. The model supports reasoning, coding, vision, tool use, local assistants, private knowledge applications and computer use tasks.

Bonsai 2 27B has 27.8 billion parameters and requires 5.9 GB of memory, more than nine times less than its full precision counterpart. PrismML says it scored 83.9 across a suite of 20 benchmarks, retaining 98.2 percent of Qwen3.8 27B's aggregate score of 85.4. It can generate up to 143 tokens per second on an NVIDIA GeForce RTX 5090.

The model was trained using Google v5 TPUs and is optimized for consumer CPUs and edge GPUs. It is available to download for free under the Apache 2.0 license starting September 17, 2026.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.