SemiAnalysis has calculated how big that gap really is. After testing subscription tiers from both OpenAI and Anthropic – running long-horizon coding and agentic tasks until weekly...
But how much is the data you’re giving them worth? The other option is don’t give them your money or your data. The Qwen 3.6 MoE model with OpenCode is running pretty well on my RTX 4060 gaming laptop. According the Codscus YouTube channel, it even runs decently in as little as 6GB of VRAM.
But how much is the data you’re giving them worth? The other option is don’t give them your money or your data. The Qwen 3.6 MoE model with OpenCode is running pretty well on my RTX 4060 gaming laptop. According the Codscus YouTube channel, it even runs decently in as little as 6GB of VRAM.
TBH local models aren’t as good as cloud. Even with 16GB VRAM you aren’t getting anywhere close to >100GB cloud LLM
Not $14k lmao