mlboydaisuke/qwen3.5-0.8B-CoreML

Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes)

Link the card back to its collection and the request box

v1.8.0: full-vocab rep_penalty path — embed_weight.bin

v1.8.0: full-vocab rep_penalty path — weight.bin

v1.8.0: full-vocab rep_penalty path — model.mlmodel

v1.8.0: full-vocab rep_penalty path — Manifest.json

v1.8.0: full-vocab rep_penalty path — weight.bin

v1.8.0: full-vocab rep_penalty path — model.mlmodel

v1.8.0: full-vocab rep_penalty path — Manifest.json

v1.8.0: full-vocab rep_penalty path — weight.bin

v1.8.0: full-vocab rep_penalty path — model.mlmodel

v1.8.0: full-vocab rep_penalty path — Manifest.json

v1.8.0: full-vocab rep_penalty path — weight.bin

v1.8.0: full-vocab rep_penalty path — model.mlmodel

v1.8.0: full-vocab rep_penalty path — Manifest.json

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

docs: add file picker + standalone Python usage + tokenizer source

Add INT8 palettized decode (754 MB, 50% of fp16, parity preserved)

Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith)

initial commit