Alio Leuchtmann PRO

AlioLeuchtmann

·

AI & ML interests

LLMs VLMs FineTuning Knowledge Distillation

Recent Activity

liked a model 11 days ago

JahJedi/sageattention-flashattn-blackwell-cu130-torch211-cp312

liked a model 21 days ago

Qwen/Qwen-AgentWorld-35B-A3B

new activity 23 days ago

Qwen/Qwen3.6-27B-FP8:Cannot run on RTX PRO 6000 Blackwell + WSL2 — Mamba state cache OOM

View all activity

Organizations

Articles 3

Article

RTX PRO 6000 Blackwell 96GB vs GH200: LLM Fine-Tuning Benchmark (Qwen3.5 SFT)

Article

3

Qwen3.5 Full Multimodal SFT Example (Arm64 GH200)

View all Articles

models 2

AlioLeuchtmann/Qwen2.5_3B_VL_PDF_ROTATION_DETECTION_MK1

Image-Text-to-Text • 4B • Updated Jun 29, 2025 • 13 • 1

AlioLeuchtmann/ALIO-SQL-7B

Text Generation • 8B • Updated May 29, 2025 • 7 • 1

datasets 3

AlioLeuchtmann/LongBench-v2-with-len-in-token

Viewer • Updated Jan 17 • 503 • 35

AlioLeuchtmann/BIRD_SPIDER_Qwen2.5-Coder-32B

Updated May 29, 2025 • 12

AlioLeuchtmann/MeetingBank-transcript-de

Viewer • Updated Apr 18, 2025 • 5.17k • 40