Qwen/Qwen3.8-Flash-Next
Image-Text-to-Text • 180B • Updated • 830k • • 5.65k
👋 Open to Work
OtsoaD
OtsoaD
·
AI & ML interests
Local LLM Deployment: Optimizing models like Qwen, Ollama, and Hermes Agent for production use.
AI/API Integration: Building AI agents with Claude Code and automating workflows via n8n.
Full-Stack Software Architecture: Designing systems combining JavaScript/TypeScript, Python, and cloud infrastructure for SaaS solutions.
Recent Activity
liked a model 29 days ago
Qwen/Qwen3.8-Flash-Next new activity about 1 month ago
ornith-ai/Ornith-1.5-35B-A3B-GGUF:internal params vs recommended liked a model about 1 month ago
ornith-ai/Ornith-1.5-35B-A3B-MLXOrganizations
None yet
liked a
model 29 days ago
internal params vs recommended
1
#12 opened about 1 month ago
by 
KottCh
liked a
model about 1 month ago
upvoted a collection about 1 month ago
MTP speculation is net-negative under Ollama's GGUF path, strongly positive under MLX (measured on M4 Pro)
5
#80 opened about 1 month ago
by OtsoaD
liked a
model about 1 month ago
CONGRATS TO QWEN TEAM !
❤️ 13
#18 opened about 1 month ago
by OtsoaD
liked a
model about 1 month ago
upvoted an article about 1 month ago
Article
Making Knowledge Distillation Cheap Enough to Run at Scale
MultiverseComputingCAI
• • 42 liked 2
models about 1 month ago
liked a
model about 2 months ago