Scott Leimroth

scottleimroth

·

https://www.scottleimroth.com

AI & ML interests

Local LLM benchmarking and model tuning on NVIDIA DGX Spark. Quantisation, speculative decoding, abliteration.

Recent Activity

updated a model 4 days ago

leimroth-lab/Aletheia-LR9

published a model 4 days ago

leimroth-lab/Aletheia-LR9

new activity 15 days ago

vcruz305/DSV4.1-Flash-1017-DERISKED-EXL3-1.61bpw:config.json ships the base model's FP8 quantization_config, so the DSpark draft fails to start

View all activity

Organizations

liked a model 19 days ago

dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-UNCENSORED

Text Generation • 303B • Updated 19 days ago • 2.08k • 25

liked 3 models about 1 month ago

nvidia/Qwen3.8-27B-NVFP4

Text Generation • 18B • Updated Sep 17 • 241k • 231

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated about 2 hours ago • 7.85M • • 19.3k

z-lab/Qwen3.8-27B-DFlash2

Text Generation • 2B • Updated Aug 19 • 54.1k • 331