LLM EXPLORER 62,323 MODELS INDEXED

Ternary Bonsai 2 27B MTPLX Optimized Speed by Youssofal

By Youssofal · 1506 downloads
HF Repo ↗ Copy URL

Ternary Bonsai 2 27B MTPLX Optimized Speed is an open-source language model by Youssofal. Features: 27b LLM, VRAM: 0.2GB, License: apache-2.0, LLM Explorer Score: 0.36.

  2-bit   27b   Apple-silicon Base model:merge:prism-ml/tern... Base model:merge:qwen/qwen3.8-... Base model:prism-ml/ternary-bo...   Base model:qwen/qwen3.8-27b   Bonsai   Claude-code   Coding   Conversational   Image-text-to-text   Local-ai   Local-llm   M3   M4   M5   M5-max   Mac-mini   Macbook-air   Macbook-pro   Macos   Mlx   Mtp   Mtplx   Multi-token-prediction   Opencode   Prism hadamard qwen35   Prismml   Qwen3-8   Qwen3.8   Region:us   Safetensors   Speculative-decoding   Ternary   Vision
Model Card on HF 🤗: https://huggingface.co/Youssofal/Ternary-Bonsai-2-27B-MTPLX-Optimized-Speed 

Ternary Bonsai 2 27B MTPLX Optimized Speed Parameters and Internals

LLM NameTernary Bonsai 2 27B MTPLX Optimized Speed
Repository 🤗https://huggingface.co/Youssofal/Ternary-Bonsai-2-27B-MTPLX-Optimized-Speed 
Base Model(s)  Ternary Bonsai 2 27B Mlx 2bit   Qwen/Qwen3.8-27B   prism-ml/Ternary-Bonsai-2-27B-mlx-2bit   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM0.2 GB
Updated2026-09-27
MaintainerYoussofal
Model Typeprism_hadamard_qwen35
Model Files  8.6 GB   0.2 GB
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace