LFM2.5-DSpark: Up to 3.2x Faster Inference from H100 to MacB
Alephinitesimal
15 points
0 comments
August 21, 2026
Related Discussions
Found 5 related stories in 67.5ms across 6,054 title embeddings via pgvector HNSW
- Apple Silicon and macOS VMs: Faster LLM Inference with llama.cpp frabonacci · 289 pts · August 11, 2026 · 59% similar
- H3-metal – Native MiniMax-H3 inference for Apple Silicon swyx · 172 pts · August 11, 2026 · 53% similar
- Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac gitpusher42 · 720 pts · July 29, 2026 · 52% similar
- Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs Argonautlabs · 247 pts · September 08, 2026 · 50% similar
- Introducing Muse Spark 1.3 scrlk · 64 pts · September 02, 2026 · 50% similar