Hugging Face's logo

ToPo-ToPo
/
Qwen3.6-27B-mlx-bf16

Image-Text-to-Text
MLX
Safetensors
qwen3_5
vision
conversational
Model card Files
xet
 Community

ToPo-ToPo/Qwen3.6-27B-mlx-bf16

MLX bf16 conversion of Qwen/Qwen3.6-27B for Apple Silicon (mlx-vlm).

Provenance (self-converted from official weights)

  • Source: Qwen/Qwen3.6-27B (license: apache-2.0)
  • Tool: mlx-vlm 0.6.3 — mlx_vlm.convert --hf-path Qwen/Qwen3.6-27B --mlx-path . --dtype bfloat16
  • Effective: 16.0 bits/weight
  • Validation: reproduced geometrically exact CAD output in an agentic CAD+FEM pipeline (volumes match the reference mlx-community conversion).

Usage 

from mlx_vlm import load, generate
model, processor = load("ToPo-ToPo/Qwen3.6-27B-mlx-bf16")
Downloads last month
69
Safetensors
Model size
27B params
Tensor type
BF16
·
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ToPo-ToPo/Qwen3.6-27B-mlx-bf16

Base model

Qwen/Qwen3.6-27B
Finetuned
(260)
this model

Collection including ToPo-ToPo/Qwen3.6-27B-mlx-bf16