What are the hardware requirements for Ternary Bonsai 27B Mlx 2bit?

Ternary Bonsai 27B Mlx 2bit requires approximately 8.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ternary Bonsai 27B Mlx 2bit and how large is it?

Ternary Bonsai 27B Mlx 2bit is developed by prism-ml, a model with 27b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Ternary Bonsai 27B Mlx 2bit?

Ternary Bonsai 27B Mlx 2bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ternary Bonsai 27B Mlx 2bit by prism-ml — VRAM 8.5GB

Name: Ternary Bonsai 27B Mlx 2bit
Author: prism-ml

Ternary Bonsai 27B Mlx 2bit is an open-source language model by prism-ml. Features: 27b LLM, VRAM: 8.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.42.

2-bit 2bit Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.6-27b Bonsai Conversational Cuda Hybrid-attention Metal Mlx On-device Prismml Quantized Qwen3 5 Region:us Safetensors Ternary

Model Card on HF 🤗: https://huggingface.co/prism-ml/Ternary-Bonsai-27B-mlx-2bit

Ternary Bonsai 27B Mlx 2bit Parameters and Internals

LLM Name	Ternary Bonsai 27B Mlx 2bit
Repository 🤗	https://huggingface.co/prism-ml/Ternary-Bonsai-27B-mlx-2bit
Base Model(s)	Qwen/Qwen3.6-27B Qwen/Qwen3.6-27B
Model Size	27b
Required VRAM	8.5 GB
Updated	2026-08-09
Maintainer	prism-ml
Model Type	qwen3_5
Model Files	8.5 GB
Quantization Type	2bit
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Ternary Bonsai 27B Mlx 2bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Ternary Bonsai 27B Mlx 2bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 27B OptiQ 4bit	256K / 18.7 GB	13065	59
Bonsai 27B Mlx 1bit	0K / 5.1 GB	809309	205
Qwen3.8 27B MLX 5bit	0K / 19.5 GB	4675044	2
...onsai 2 27B CRACK Ternary JANG	0K / 8.1 GB	2689	13
Qwen3.6 27B MLX 8bit	0K / 29.4 GB	879145	14
Qwen3.6 27B MLX 6bit	0K / 22.7 GB	812977	2
Qwen3.8 27B 8bit	0K / 29.4 GB	13892	33
Qwen3.6 27B MLX 4bit	0K / 16 GB	846861	16
Ternary Bonsai 2 27B Vllm	0K / 10.3 GB	2048	4
...onsai 2 27B CRACK 1.75bit JANG	0K / 6.4 GB	1457	3

Note: green Score (e.g. "73.2") means that the model is better than prism-ml/Ternary-Bonsai-27B-mlx-2bit.