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: 21 commits

mlboydaisuke's picture

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

82700f4 verified about 2 months ago

qwen3_5_0_8b_decode_chunks_mlkv
v1.8.0: full-vocab rep_penalty path — embed_weight.bin 6 months ago
qwen3_5_0_8b_decode_fp16_mseq128.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 6 months ago
qwen3_5_0_8b_decode_int8_mseq128.mlpackage
Add INT8 palettized decode (754 MB, 50% of fp16, parity preserved) 6 months ago
qwen3_5_0_8b_fp16_seq64.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 6 months ago
qwen3_5_0_8b_prefill_stateful_fp16_seq64.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 6 months ago
qwen3_5_chunk_a.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 6 months ago
qwen3_5_chunk_b.mlpackage
Initial upload: Qwen3.5-0.8B CoreML variants (decode + prefill + chunks + monolith) 6 months ago
.gitattributes

1.52 kB
initial commit 6 months ago
README.md

6.45 kB
Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes) about 2 months ago