mlboydaisuke
/

qwen3.5-0.8B-CoreAI

Text Generation

Model card Files Files and versions

qwen3.5-0.8B-CoreAI

10.9 GB

Ctrl+K

Ctrl+K

1 contributor

History: 25 commits

mlboydaisuke's picture

gen-cards: regenerate Use-it block

c50a10c verified 16 days ago

gpu-pipelined-b2
Add b2 (beta3-loadable) bundle under gpu-pipelined-b2/qwen3_5_0_8b_decode_int8hu_block32_sym/ (b1 retained) 25 days ago
gpu-pipelined
Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle 22 days ago
ios-ane
iOS ANE best: dynamic int8 (14.7 tok/s) about 2 months ago
ios-gpu
ios-gpu: add qwen3_5_0_8b_ios_hc_prefill_q16_b2048_int8.aimodel about 2 months ago
macos
macOS GPU best: dynamic int8 (58.5 tok/s release) about 2 months ago
.gitattributes

3.18 kB
Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle 22 days ago
README.md

11.4 kB
gen-cards: regenerate Use-it block 16 days ago
config.json

306 Bytes
Add root config.json (Hub download-stats query file + framework pointer) about 2 months ago