Ternary-Bonsai-2-9B: 2-bit ternary vision-language model trends on Hugging Face for on-device use
prism-ml · hf · 2026-10-21
Ternary-Bonsai-2-9B (GGUF) from prism-ml is trending on Hugging Face. It's an image-text-to-text model released in ternary 2-bit quantization via llama.cpp, with CUDA and Metal backends for on-device inference.
- Hybrid-attention architecture with vision support
- Targets local/on-device deployment at very low bit-width
- A notable low-compute option for local VLM enthusiasts
More from Infra
- Neoclouds now gross ~$38 per GPU-hour at 155 trillion tokens/day per cluster — basedjensen · 2026-10-21
- DeepSeek reportedly earns $38 per GPU-hour on tokens — what does it mean for GPU pricing? — andrew_n_carr · 2026-10-21
- Hyperscaler insider: GPU order-to-install lead time has always been 1–2 quarters — BenBajarin · 2026-10-21
- Efficient Computer's Electron E1 chip claims 100x energy efficiency, named a Time Best Invention — rebeccakaden · 2026-10-21
- Nemotron 3.5 Super hits 3M token pool on a single RTX PRO 6000 via SGLang — TechNerd10191 · 2026-10-21
- vLLM gains sleep mode on Apple Silicon: idle model servers now return KV cache memory — abhijithneil · 2026-10-21