How much RAM does Ternary-Bonsai-27B-unpacked need?

Ternary-Bonsai-27B-unpacked needs about 59 GB of memory at Published quantization with 4K context. The download itself is 55 GB; the extra covers the context cache and a runtime allowance.

Can I run Ternary-Bonsai-27B-unpacked on a laptop?

Yes. It fits a machine with 128GB RAM, for example MacBook Pro M5 Max (128GB).

Ternary-Bonsai-27B-unpacked: hardware requirements

Ternary-Bonsai-27B-unpacked needs about 59 GB of memory at Published quantization: a 55 GB download plus room for context and a runtime allowance. That fits a machine with 128GB RAM.

Parameters

27B

Tier

Needs a good desktop

Licence

See model card

Released

2026-09-17

Will it run on your machine?

8GB RAMNot enough memory 16GB RAMNot enough memory 24GB RAMNot enough memory 32GB RAMNot enough memory 64GB RAMTight fit 128GB RAMRuns well 8GB VRAMNot enough memory 12GB VRAMNot enough memory 16GB VRAMNot enough memory 24GB VRAMNot enough memory 32GB VRAMNot enough memory

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

Quant	Download	RAM @ 4K	RAM @ 32K	Source
Published	55 GB	59 GB	67 GB	prism-ml/Ternary-Bonsai-27B-unpacked

Download sizes are measured from the published files named in the Source column. The RAM columns add the context cache, calculated from the model's configuration, and a runtime allowance of 10% of the download (at least 0.5GB, at most 3GB).

Model card on HuggingFace →API specs & pricing →Verified 2026-10-23Listed for 120 days after release