Views
No views yet
microsoft/Lens-Turbo
for on-device Apple-Silicon inference via mlx-gen's
mlx-gen-lens provider (SceneWorks). The heavy components are packed offline so a tier loads
directly with no dense transient and no in-app quantization (epic 8506, sc-8763).transformer/, text_encoder/, vae/, tokenizer/, scheduler/, model_index.json):| Tier | Dir | What is packed |
|---|---|---|
| Q4 (default) | q4/ | DiT + gpt-oss encoder MoE experts → MLX group-64 affine 4-bit |
| Q8 | q8/ | DiT + gpt-oss encoder MoE experts → MLX group-64 affine 8-bit |
| bf16 | bf16/ | dense mirror of the source (no quantization) |
.quantize scope):img_in/txt_in/proj_out + every block's fused-QKV attention projections
(img_qkv/txt_qkv/to_out.0/to_add_out) and SwiGLU MLPs. The timestep embedder, AdaLN
modulations, and all norms stay full precision.experts.{gate_up,down}_proj.{weight,scales,biases}). The
router / attention / embeddings / norms stay dense.mlx-gen-lens convert/quant byte-identity tests) and by an on-device render gate.microsoft/Lens-Turbo. This is a format re-host; all model weights and credit
belong to the original authors (Microsoft Research).