---
type: "post"
id: "kapitsa-v0-2-15-an-open-source-apple-e8f061"
slug: "kapitsa-v0-2-15-an-open-source-apple-e8f061"
title: "Kapitsa v0.2.15, an open-source Apple Silicon inference engine for Qwen and Nemotron, ships stability fixes and faster MoE prefill"
description: "NACE AI released Kapitsa v0.2.15, an open-source inference engine targeting Apple Silicon."
retrieval_nugget: "NACE AI released Kapitsa v0.2.15, an open-source inference engine targeting Apple Silicon."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["inference"]
entities: ["Kapitsa","NACE AI","KFlash","Flint"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Kapitsa v0.2.15 adds stability fixes and faster MoE prefill for its Apple Silicon inference engine; the archive covers related Apple Silicon inference and Nemotron, not this release."
prior_refs: ["memory:0c65482b-792e-8c7b-a3a5-bbb7ae8314f4","memory:dcccaa7e-e997-8f78-a635-48ce28e99991"]
source_url: "https://github.com/nace-ai/kapitsa/releases/tag/v0.2.15"
source_urls: ["https://github.com/nace-ai/kapitsa/releases/tag/v0.2.15"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:kapitsa-v0-2-15-an-open-source-apple-e8f061"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/kapitsa-v0-2-15-an-open-source-apple-e8f061/","markdown":"https://newruntime.com/posts/kapitsa-v0-2-15-an-open-source-apple-e8f061.md","json":"https://newruntime.com/posts/kapitsa-v0-2-15-an-open-source-apple-e8f061.json"}
---

# Kapitsa v0.2.15, an open-source Apple Silicon inference engine for Qwen and Nemotron, ships stability fixes and faster MoE prefill

## Retrieval answer

NACE AI released Kapitsa v0.2.15, an open-source inference engine targeting Apple Silicon.

NACE AI released Kapitsa v0.2.15, an open-source inference engine targeting Apple Silicon. The GitHub release lists a server-crash fix for systemone when a question exceeds 2,048 tokens, plus rejection of overly deep JSON before it reaches the parser.

The release reports faster prefill for a 35B-A3B mixture-of-experts model on an M5: 7.1% at 4K tokens and 6.5% at 16K tokens. Kapitsa says the resulting output is bitwise identical. It also adds kapitsa-systemone and kapitsa-drex-pointer to release packages, and changes releases to fail if the Homebrew tap cannot be updated.

Other changes include wrapping every decode with KFlash, with prompt-lookup rows opt-in through `NI_KFLASH_BUDGET=1`. The notes also describe a Flint decode issue producing garbage output on an M5 Ultra, not verified on a GPU, and a terminal-query leak fix. The source does not provide independent benchmarks, general performance figures across hardware, or evidence that the listed fixes have been validated outside the project’s stated tests.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Inference](https://newruntime.com/topics/inference.md): Explore the inference topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)