🤝 Open to Collab, Open to Learn\Work
Dawid J
psychofanPLAYS
AI & ML interests
yes
Recent Activity
new activity 6 minutes ago
Qwen/Qwen3.8-27B:Why Qwen3.8-27B overthinks? Here the reason and partial fix confirmed by benchmarks. new activity 22 minutes ago
Qwen/Qwen3.8-27B:5090 Qwen3.8-27B NVFP4 Best setup for real world use (vLLM wins over llama) new activity 30 minutes ago
Qwen/Qwen3.8-27B:Horrible model .... Overthink eats all context tokensOrganizations
None yet