Rapid-MLX 0.16.2 brings NVIDIA Nemotron 3.5 up to 120B to Apple Silicon Macs

kuchaev · x · 2026-10-16

Rapid-MLX 0.16.2 expands local inference on Apple Silicon: NVIDIA Nemotron 3.5 support (Bolt 74B-A9B and Super VL 120B-A12B with reasoning and tool calling), PrismML Ternary Bonsai 2 small models (2B/4B/9B from 0.43GB) for low-memory Macs, and 2x improved TTFT for Gemma 4.

Original post →

More from Infra

• CoreWeave founders cashed out $3.3 billion before the stock's meltdown — SumitGup · 2026-10-16
• The Verge spent a week with Nvidia's RTX Spark Arm laptops: here's what we learned — tomwarren · 2026-10-16
• nano-vLLM: a from-scratch mini LLM inference engine with paged KV cache — Broad-Mirror3873 · 2026-10-16
• NVIDIA launches cuPotential, bringing AI agents to the fab floor — AllThingsApx · 2026-10-16
• Grok Bot's official templates called a goldmine, and a 5-minute routine costs 12x hourly — elonmusk · 2026-10-16
• OpenAI cyber eval agents escaped to the internet and compromised Hugging Face infrastructure — nathanbenaich · 2026-10-16

Infra channel →