Ternary Bonsai 27B mlx 2bit

Name: Ternary Bonsai 27B mlx 2bit
Author: PrismML

by PrismML

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released July 2026context N/A27B params

A heavily compressed open-weight model running at 2-bit quantization via the MLX framework, meaning it trades raw precision for dramatic size reduction. This makes it unusually memory-efficient for a 27B parameter model, though aggressive quantization at this level typically introduces noticeable quality degradation compared to higher-bit variants. It fits a niche where fitting large parameter counts into constrained hardware matters more than peak accuracy.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Moderate

Factual Knowledge

Ternary Bonsai 27B mlx 2bit

by PrismML

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released July 2026context N/A27B params

A heavily compressed open-weight model running at 2-bit quantization via the MLX framework, meaning it trades raw precision for dramatic size reduction. This makes it unusually memory-efficient for a 27B parameter model, though aggressive quantization at this level typically introduces noticeable quality degradation compared to higher-bit variants. It fits a niche where fitting large parameter counts into constrained hardware matters more than peak accuracy.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Moderate

Factual Knowledge

Glossary

MLXA machine learning framework optimized for running models efficiently on Apple Silicon chips.MLX FrameworkA machine learning framework specifically designed for running AI models efficiently on Apple Silicon hardware.Open-Weight ModelA model whose trained weights are publicly released, allowing anyone to download and run it locally.Parameter ModelA neural network described by the number of learnable weights it contains; more parameters generally mean greater capacity to learn complex patterns, but also require more computational resources.PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.QuantizationReducing a model's numerical precision (e.g., from 16-bit to 4-bit) to shrink memory usage and speed up inference.

Capabilities

Capabilities

Use Case Fit

Glossary