Palm-Infra open-sourced: Run 284B models on MacBook via SSD offloading
dr_cintas · x · 2026-08-26
Tencent's Palm-Infra framework enables running massive MoE models on Apple Silicon by streaming experts directly from SSD. Benchmarks show DeepSeek-V4-Flash (284B) decoding at 5.71 tps and a 122B model at 16.53 tps on an M5 Pro with 20GB memory, achieving capabilities previously impossible with llama.cpp.
Related event: Tencent Open-Sources Palm-Infra, Running 284B Models on a MacBook(2 posts)→
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15