Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
mlboydaisuke
/
Qwen3.8-27B-CoreAI
like
0
Image-Text-to-Text
qwen3_5
coreai
aimodel
apple-silicon
on-device
qwen3.8
hybrid
gated-deltanet
vlm
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Qwen3.8-27B-CoreAI
/
gpu-pipelined
60.5 GB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
mlboydaisuke
Qwen3.8-27B: remove pf32 VL decoder (fp16 overflow on real images; pf16 replaces it)
927bbee
verified
about 17 hours ago
qwen3_8_27b_decode_int8hu_block32_sym
Qwen3.8-27B: qwen3_8_27b_decode_int8hu_block32_sym
about 21 hours ago
qwen3_8_27b_vision_fp16
Qwen3.8-27B: qwen3_8_27b_vision_fp16
about 21 hours ago
qwen3_8_27b_vl_decode_int8hu_block32_sym_pf16
Qwen3.8-27B: VL decoder pf16 (pf32 chunk overflows fp16 content-dependently)
about 17 hours ago
