I split my coding work between Claude, Qwen3-Coder and Gemma 4, and it costs less than paying for one subscription
… As per my analysis, coding is uniquely expensive on a cloud model for three major reasons. …
Search
Tracked topic
Alibaba
Live now
Alibaba's RISC-V CPU, XuanTie C950, Runs Qwen-3.8 27B at 30 tps
I tested a local LLM against a frontier cloud model, and the gap was smaller than I expected
… This isn't local models beating the cloud, because they don't overall . …
I run a 24GB GPU instead of paying for Claude or Codex, and Qwen 3.6 keeps up more than I expected
… My hardware, my rules Consistency is key and cloud-based models keep changing the rules It feels like every other week, there are some rule changes by cloud LLM companies to reduce my usage. …
I ran Gemma, Llama, and Qwen on my phone, and only one of them is worth the storage
… It's Alibaba's small dense model that's strong on reasoning and also has vision. …
I ran Gemma 4 and Qwen 3.5 for the same local tasks, and one pulled miles ahead
… The responses feel closer to a cloud chatbot in tone, it's better with visual work, and it's more lightweight, and I can access it from pretty much anywhere. …
I vibe coded with Qwen 3.6 on a platform it had never seen, and the model was never the bottleneck
… Getting the cloud to my LAN was the only difficult part. …