Language body: MXFP8, 8-bit, group size 32
MoE gate overrides: affine 8-bit, group size 64
Vision tower: source BF16, 333 tensors
Architecture: Qwen3.5 MoE multimodal, 40 language layers, 256 experts
Tokenizer, chat template, processor metadata, and vision features preserved from the pinned source

This standard artifact disables MTP metadata and does not include an MTP sidecar.

Local qualification

Structural inspection: pass (1,658 indexed tensors; 512 quantized weights; 80 MoE gate overrides)
Shard index: pass; no stale or missing shards
Strict MLX-LM and MLX-VLM lazy load: pass
Cross-variant tokenizer, template, processor, and vision-shard parity: pass
Vision features: source BF16 tensor payload preserved

Basic use

bash

python -m mlx_vlm.generate \
  --model <local-path-or-repo-id> \
  --image image.jpg \
  --prompt "Describe this image." \
  --max-tokens 256

Review the upstream model card for intended use, training, license, benchmarks, and deployment considerations. Quantization does not change the upstream model's safety characteristics.

Shiftedx/ornith-1.0-35b-mxfp8-mlx

ornith-1.0-35b-mxfp8-mlx

Format

Local qualification

Basic use

Shiftedx/
ornith-1.0-35b-mxfp8-mlx