mlboydaisuke
/

qwen3.5-0.8B-CoreML

Text Generation

Model card Files Files and versions

qwen3.5-0.8B-CoreML

8.56 GB

Ctrl+K

Ctrl+K

1 contributor

History: 19 commits

mlboydaisuke's picture

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

0794478 verified 14 days ago

qwen3_5_0_8b_decode_chunks_mlkv
v1.8.0: full-vocab rep_penalty path — embed_weight.bin 14 days ago
qwen3_5_0_8b_decode_fp16_mseq128.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 21 days ago
qwen3_5_0_8b_decode_int8_mseq128.mlpackage
Add INT8 palettized decode (754 MB, 50% of fp16, parity preserved) 21 days ago
qwen3_5_0_8b_fp16_seq64.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 21 days ago
qwen3_5_0_8b_prefill_stateful_fp16_seq64.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 21 days ago
qwen3_5_chunk_a.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 21 days ago
qwen3_5_chunk_b.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 21 days ago
.gitattributes

1.52 kB
initial commit 21 days ago
README.md

5.98 kB
Upload README.md with huggingface_hub 15 days ago