Views
No views yet
Ternary-Bonsai-27B-dspark-bf16.gguf
— no safetensors export exists upstream). This repo is a 1:1, lossless repack of that file:
tensor names remapped from llama.cpp/GGUF names back to the original HF Qwen3DSparkModel
export layout (the exact inverse of PrismML's own conversion/dspark.py), all weights kept at
their source precision (BF16), plus a synthesized DeepSpec-style config.json from the GGUF
metadata. No weights were modified, quantized, fine-tuned, or otherwise altered.[1, 16, 31, 46, 61] (of 64)1pip install mlx-dspark # needs mlx >= 0.32.0
2mlx-dspark generate --model prism-ml/Ternary-Bonsai-27B-mlx-2bit \
3 --max-draft auto --prompt "Implement binary search in Python."--max-draft auto calibrates the speculation depth to your machine and content
(measured on an M4 Pro: ≈1.1–1.2× on code/structured output; it parks itself on content where a
2-bit target's fast plain step can't be beaten). The drafter is quantized to 4-bit at load
(≈2 GB resident; drafter precision does not affect acceptance).gguf_convert.py.