Phosphene Update: Run MiniMax H3 on 48GB Macs, 10s Single-Pass Renders
cocktailpeanut · x · 2026-08-12
Phosphene 3.7.0 brings massive optimizations for running MiniMax H3 locally on Macs.
- Lower RAM requirement: Previously requiring 64GB, H3 can now run on 48GB Macs.
- Faster drafts: Draft generation takes roughly 1 minute, significantly speeding up iteration.
- True 10-second renders: Achieves a real single-pass 10-second video, eliminating drift issues from stitched clips.
Related event: Phosphene 3.7.0 Slashes Memory for MiniMax H3 on Mac(2 posts)→
More from Infra
- Open Source AI Summit Announces Talk on LLM Inference Engine Optimization — zainhas · 2026-08-12
- Google's PROMPTS: Multi-Agent Framework Boosts LLM Training Performance by 434% — rohanpaul_ai · 2026-08-12
- Running MiniMax H3 on Low VRAM Fried My GPU, Beware — ROBOTTTTT13 · 2026-08-12
- StarCloud Explores Space Data Centers: Launching AI Hardware into Orbit — DavidLinthicum · 2026-08-12
- gakonst adds confidential compute support to nanocodex for verifiable confidential AI — AccBalanced · 2026-08-12
- Alibaba Cloud's CUBE 5.0 Modular Design Builds AI Data Centers in 100 Days at 10% Lower Cost — rohanpaul_ai · 2026-08-12