LLM EXPLORER 58,873 MODELS INDEXED

Ternary Bonsai 27B Mlx Lossless 1.75bpw by inductiveML

By inductiveML · 312 downloads
HF Repo ↗ Copy URL

Ternary Bonsai 27B Mlx Lossless 1.75bpw is an open-source language model by inductiveML. Features: 27b LLM, VRAM: 5.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  8-bit   Apple-silicon Base model:finetune:prism-ml/t... Base model:prism-ml/ternary-bo...   Conversational   Gguf   Lossless   Mlx   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Ternary
Model Card on HF 🤗: https://huggingface.co/inductiveML/Ternary-Bonsai-27B-mlx-lossless-1.75bpw 

Ternary Bonsai 27B Mlx Lossless 1.75bpw Parameters and Internals

LLM NameTernary Bonsai 27B Mlx Lossless 1.75bpw
Repository 🤗https://huggingface.co/inductiveML/Ternary-Bonsai-27B-mlx-lossless-1.75bpw 
Base Model(s)  prism-ml/Ternary-Bonsai-27B-gguf   prism-ml/Ternary-Bonsai-27B-gguf
Model Size27b
Required VRAM5.9 GB
Updated2026-08-18
MaintainerinductiveML
Model Typeqwen3_5
Model Files  4.3 GB: 1-of-2   1.6 GB: 2-of-2
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureQwen3_5ForCausalLM
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Ternary Bonsai 27B Mlx Lossless 1.75bpw

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 Whittle 16B256K / 2.4 GB17191
...Uncensored Heretic Abliterated256K / 53.8 GB22712
...en3.6 27B OBLITERATED MLX 4bit256K / 15.1 GB6463
Qwen3.6 27B Bnb 4bit256K / 17.7 GB11940
Qwen3.8 27B Abliteratex256K / 53.9 GB3216
Qwen3.6 27B OBLITERATED256K / 53.6 GB15137184
...wen3.8 P44w75 16.8B Unrepaired256K / 2.4 GB9291
...maAQUA Gridbook 13GB 5080 Vllm256K / 13 GB2872
Focus Red256K / 53.8 GB4161
...2 Abliterated OptiQ 3.7bpw Mlx256K / 13.4 GB672714
Note: green Score (e.g. "73.2") means that the model is better than inductiveML/Ternary-Bonsai-27B-mlx-lossless-1.75bpw.