DeepSeek v4 Pro on 4×GB300: Sub-Agent Hits 188 tok/s
Xianbao_QIAN · x · 2026-07-03
A user deployed DeepSeek v4 Pro + DSpark on 4 GB300 GPUs, integrating it into opencode with default settings. Tests showed each sub-agent achieving a blistering 188 tok/s. The author described the coding experience as returning to the intuitive feel of native JS. Expressing immense excitement over dedicated inference compute, the author is even considering purchasing GB300 hardware to fully embrace an unlimited, dedicated agent lifestyle without waiting for slow LLM responses.
More from coding & agent
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Investment Analyst Asks How to Build a Claude-Based Diligence Agent Stack — Careless_Tie2286 · 2026-09-11
- Treating agents like 50 First Dates: a 3-layer context system so every conversation doesn't start from zero — evielync · 2026-09-11