Bonsai-27B Q1_0 GGUF (RLX staging)

prism-ml Bonsai-27B packed Q1_0 GGUF for RLX Qwen3.5 runner.

| Field | Value |

|---|---|

| Kind | Staging redistrib of an upstream checkpoint for RLX runners. |

| RLX crate | rlx-qwen35 |

| Upstream | https://huggingface.co/prism-ml/Bonsai-27B-gguf |

Quick start

hf download eugenehp/bonsai-27b-gguf --local-dir .
cargo run -p rlx-qwen35 --release -- --weights Bonsai-27B-Q1_0.gguf --device metal

Clone rlx-models, place this repo under weights/lm/bonsai-27b-gguf (or pass the path explicitly), then:

cargo run -p rlx-qwen35 --release -- --weights Bonsai-27B-Q1_0.gguf --device metal

Apache License 2.0 — see LICENSE. Inherit upstream terms when redistributing.

Original weights and authorship: https://huggingface.co/prism-ml/Bonsai-27B-gguf

This Hub repo exists so RLX recipes have a stable fetch target. When you only need the upstream checkpoint, prefer the Upstream link above.

Question 2

What license applies to eugenehp/bonsai-27b-gguf?

Accepted Answer

License: apache-2.0. Verify terms on Hugging Face before commercial use.

Question 3

How do I run eugenehp/bonsai-27b-gguf locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does eugenehp/bonsai-27b-gguf need?

Accepted Answer

Runs locally from ~3.54 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).