Andreas Bisiadis

AndreasBis

·

https://www.kaggle.com/andreasbis

AI & ML interests

SGLang/vLLM inference; any LLM that fits on a single RTX PRO 6000 Blackwell

Recent Activity

liked a model 1 day ago

peasantsmith/GLM-5.3-Flash-Maya-GGUF

liked a model 4 days ago

MiniMaxAI/MiniMax-H3-Image

liked a model 16 days ago

mistralai/Mistral-Large-4-1T-A52B

View all activity

Organizations

None yet

New activity in nvidia/Qwen3.8-Flash-Next-FP4-Local 21 days ago

Serving FP4-Local on SGLang (one RTX PRO 6000, PRs open for review)

#10 opened 21 days ago by

New activity in nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 25 days ago

Loading without `trust_remote_code` fails on transformers 5.19: `_downsample_factor` has no setter

#4 opened 25 days ago by

New activity in yandex/AliceAI-Foundation-80B-A3B-Base about 2 months ago

MXFP4 or FP8?

#6 opened about 2 months ago by

New activity in meta-models/Muse-Glimmer-30B 3 months ago

Any plans for 70B-300B models?

#7 opened 3 months ago by