Daily AI news, sourcedOn Oct 21, Kapitsa 0.2, an open-source inference engine for Apple Silicon Macs, added Nemotron Nano models and Qwen3.6-35B-A3B on 16 GB Macs.
Where it stands
On Oct 21, Kapitsa 0.2, an open-source inference engine for Apple Silicon Macs, added Nemotron Nano models and Qwen3.6-35B-A3B on 16 GB Macs.
- Official
Kapitsa 0.2, an open-source inference engine for Apple Silicon Macs, adds Nemotron Nano models and Qwen3.6-35B-A3B on 16 GB Macs
GitHub (nace-ai/kapitsa) published this on Oct 21, 2026 (source: github.com).
Kapitsa 0.2.0, an open-source inference engine for Apple Silicon Macs, adds NVIDIA's Nemotron 3 Nano 4B and Nemotron Nano 9B v2 to its catalog and can run Qwen3.6-35B-A3B on a 16 GB Mac. The developers say that model reaches 52.6 tokens per second on an M1 Pro, against 38 for llama.cpp, and the release brings faster prefill on M1 chips.
Source: GitHub (nace-ai/kapitsa)
- Official
- An institution announces something that has already happened, through its own channel or a founder or executive account.
- Statement by …
- A named person's views, predictions, plans or comments, including remarks reported by media when the original is unavailable.
- Reported by …
- Only media or another third party is saying it. We name the outlet.
- Unconfirmed
- Circulating online (posts, comments, leaks). No company, named person or outlet has confirmed it.
Items older than 72 hours never go in Top stories and show their original date.