moonshotai/Kimi-K3
Image-Text-to-Text • 2.8T • Updated • 99.2k • • 8.71k
Alio Leuchtmann PRO
AlioLeuchtmann
AI & ML interests
LLMs
VLMs
FineTuning
Knowledge Distillation
Recent Activity
liked a model 2 days ago
moonshotai/Kimi-K3 liked a dataset 4 days ago
birdsql/bird_sql_dev_20251106 new activity 8 days ago
poolside/Laguna-S-2.1:Reasoning LevelsOrganizations
liked a
model 2 days ago
liked a
dataset 4 days ago
Reasoning Levels
🔥 1
2
#6 opened 8 days ago
by 
Felixkruemel
liked a
model 8 days ago
liked 5
models 10 days ago
InternScience/Agents-A1
Text Generation • 35B • Updated • 45.3k • 613
InternScience/Agents-A1-4B
Text Generation • 5B • Updated • 87.6k • • 66
ATH-MaaS/OvisOCR2
Image-Text-to-Text • 0.9B • Updated • 47.1k • 346
baidu/Unlimited-OCR
Image-Text-to-Text • 3B • Updated • 2.69M • 3.52k
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
Image-Text-to-Text • 27B • Updated • 737k • 953
How does it compare to Whisper + Pyannote ?
1
#18 opened 10 days ago
by AlioLeuchtmann
liked a
model 10 days ago
liked a
model 25 days ago
liked a
model about 1 month ago
Cannot run on RTX PRO 6000 Blackwell + WSL2 — Mamba state cache OOM
1
#10 opened 3 months ago
by 
noMugop
upvoted an article about 1 month ago
Article
QLORA SFT Distillation Effects on Qwen3.6 27B Agentic Coding Harness Fluency
bytkim
• • 9 liked a
model about 1 month ago
liked 2
models about 2 months ago
published an article about 2 months ago
Article
RTX PRO 6000 Blackwell 96GB vs GH200: LLM Fine-Tuning Benchmark (Qwen3.5 SFT)
AlioLeuchtmann
• commented on Qwen3.5 Full Multimodal SFT Example (Arm64 GH200) 5 months ago
Probably working aswell, in the past I allways used the lambdalabs vllm openai arm image when the GH200 first was available, since this hasnt been maintained anymore I have choosen the Custom build Image from the latest VLLM Version.
Would be happy to hear from you when it worked out with the official Image :)