Bonsai-27B

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

07:53

2026-07-28

marktechpost.com

artificial-intelligence

Deploying a 1-Bit Bonsai-27B Model with PrismML llama.cpp and OpenAI-Compatible Local Inference Workflows

PrismML released the 1-bit Bonsai-27B language model, deployable via a specialized fork of llama.cpp with CUDA kernels for the Q1_0_g128 GGUF format. The model requires only ~5.2 GB peak memory at 4K …

14:37

2026-07-20

dev.to

large-language-models

Bonsai-27B on a Single 3090: What Works and What Doesn't

A developer tested the Bonsai-27B model on a single RTX 3090 using a Q4_K_M GGUF quant from prism-ml, achieving ~28 tok/s at 4K context and ~19 tok/s at 16K. The model excelled at structured extractio…

// co-occurs with top 8 entities

llama.cpp 2 prism-ml 1 RTX 3090 1 Apache 2.0 1 PrismML 1 Hugging Face 1 OpenAI 1 CUDA 1

// topics top 6 topics

large language models 2 developer tools 2 ai infrastructure 1 ai research 1 artificial intelligence 1 ai tools 1