runlocal.devCheck My GPU →

Ternary Bonsai 1.7B

Apache 2.0

Edge-class ternary model — runs on phones and small embedded devices. 1.58-bit quantization at 1.7B parameters. MLX packed only today; llama.cpp / vLLM ports in progress.

Provider

PrismML

Parameters

1.7B

Context

32.768K

Released

2026-04-17

VRAM Requirements by Quantization

MethodDisk SizeVRAM RequiredFits GPUs
1.58-bit (MLX)0.5 GB0.6 GB15 GPUs

Benchmark Scores

mmlu54%
humaneval35%

Scores are approximate and may vary by quantization level.

Compatible GPUs (15)

HuggingFace

PrismML/ternary-bonsai-1.7b

View on HF →