Skip to main content
← Back to news

Bonsai-2 27B: 27B ternary reasoning that runs on a laptop

Model releases
Source:Hugging Face
Prism ML releases Bonsai-2 27B in GGUF: a 27B reasoning model with Ternary weights at 1.72 bits per weight, 5.95 GB and a 262K-Token context, retaining 98.2% of the FP16 intelligence and reaching ~47 tok/s on an Apple M5 Max laptop.
Read original article

Related articles

MiniCPM-V 4.7: the 35B MoE that runs on a smartphone with 3 GB of RAM

The first open 35B MoE (3B active) that runs fluidly on a smartphone: 13+ tok/s with 3 GB of RAM on an iPhone 17 Pro Max, OCR, video and a 21.8 GB GGUF Q4_K_M for desktop. The numbers, the three techniques, the limits.

gpt-oss: OpenAI's open reasoning model

21B total parameters but only 3.6B active, native MXFP4 weights and 128K of context: OpenAI's first open reasoning model fits in 16GB. What that means in practice.

Llama 3 and Llama 4: Meta's open family — which model runs on your hardware

From the 3.1 8B to the 4 Scout MoE with a 10M context: the Llama family in a table, what runs on 16, 48 and 128 GB of RAM, the Community license translated for the Italian business and the choice by budget.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🌱

Bonsai-2 27B

Models

27B reasoning model with ternary weights at 1.72 bits per weight, derived from Qwen3.8-27B with hybrid attention (~75% linear). In GGUF PTQ1_0 it takes 5.95 GB, retains 98.2% of the FP16 intelligence and reaches ~47 tok/s on an Apple M5 Max laptop, with a 262K-token context. Apache 2.0 license. Requires Prism ML's llama.cpp fork (ternary kernels are not in stock llama.cpp).

💻

Apple M4 Max

Hardware

Apple Silicon chip with exceptional performance for mobile development and edge inference.

💻

Apple M5 Max

Hardware

Il chip Apple Silicon di punta per l'IA locale: 18 core CPU e 40 core GPU con memoria unificata fino a 128GB a 614 GB/s. Il Neural Accelerator su ogni core GPU raddoppia la velocità dei modelli MoE in decode rispetto alla generazione M4: ~88 tok/s su gpt-oss-120b, il più veloce della classe.

💻

LM Studio

Software

Terminal-free desktop app for downloading and running GGUF models: GUI, built-in model search and a local server. The simplest way to get started.

Browse all resources