Ternary Bonsai: Top Intelligence at 1.58 Bits
Summary
A highly efficient AI model architecture using ternary weights (-1, 0, 1) that achieves competitive performance while requiring only 1.58 bits per parameter, enabling deployment on extremely constrained devices.
Similar Articles
1-Bit Bonsai Image 4B Image Generation for Local Devices
PrismML releases Bonsai Image 4B, a family of compact image generation models using 1-bit and ternary weights, enabling high-quality diffusion inference on local devices like laptops and iPhones with significantly reduced memory footprint.
@rohanpaul_ai: BitCPM-CANN just became the world’s first open-sourced 1.58-bit ternary LLM trained entirely on Chinese-developed AI in…
BitCPM-CANN is the first open-source 1.58-bit ternary LLM trained entirely on Chinese-developed AI infrastructure (Huawei Ascend 910B), offering extreme memory reduction for edge deployment.
PrismML just released Binary and Ternary Bonsai Image 4B: 1-bit/ternary text-to-image diffusion transformers that can even run 100% locally in your browser on WebGPU.
PrismML released Bonsai Image 4B models in binary and ternary quantized versions, enabling text-to-image generation to run locally in a browser via WebGPU with only 3GB size, under Apache-2.0 license.
@heyshrutimishra: Full-sized AI models now run on phones. That's BitCPM, a new open-source model from ModelBest, Tsinghua, and OpenBMB. T…
BitCPM is a new open-source model from ModelBest, Tsinghua, and OpenBMB that uses ternary weights (-1,0,1) to run full-sized AI models on phones.
WeiboAI/VibeThinker-3B
VibeThinker-3B is a 3B-parameter model that achieves frontier-level reasoning performance on math, coding, and STEM benchmarks by optimizing the Spectrum-to-Signal Principle (SSP) post-training pipeline, reaching performance comparable to much larger models.