Beamivalice PRO

beamster

·

https://github.com/beamivalice/sushi

AI & ML interests

Sushi quant for Apple Silicon

Recent Activity

posted an update about 2 hours ago

Last Qwen3.8 Flash update with STQ 2.75bpw v2.0 pack. It moves away from hybrid affine/stq format to pure STQ with +15% quality to match oQ4e. 64GB users can enjoy this while waiting for Qwen 4! Require Sushi 1.5.1 ro run.

updated a model about 3 hours ago

beamster/Qwen3.8-Flash-Next-Sushi-4bpw

updated a model about 3 hours ago

beamster/Qwen3.8-Flash-Next-Sushi-3bpw

View all activity

Organizations

None yet

liked a model 10 days ago

beamster/DeepSeek-V4.1-Flash-1017-Sushi-STQ-1.75bpw

Image-Text-to-Text • 261B • Updated 2 days ago • 1.57k • 16

liked a model 20 days ago

deepseek-ai/DeepSeek-V4.1-Flash-1017

Image-Text-to-Text • 763B • Updated 20 days ago • 260k • • 5.35k

liked a model 30 days ago

beamster/GLM-5.3-Flash-Sushi-2.4bpw

Image-Text-to-Text • 55B • Updated about 1 month ago • 889 • 11

liked a dataset about 1 month ago

XiaomiMiMo/MiMo-V2.6-RL-oss

Viewer • Updated 18 days ago • 7.68k • 293k • 1.05k

liked 2 models about 1 month ago

beamster/Qwen3.8-Flash-Next-Sushi-2bpw

Image-Text-to-Text • 21B • Updated about 3 hours ago • 1.82k • 12

beamster/Qwen3.8-Flash-Next-Sushi-2.6bpw

Image-Text-to-Text • 26B • Updated about 3 hours ago • 947 • 26