Apple Silicon costs more than OpenRouter
Running AI inference locally on Apple Silicon is more expensive than using OpenRouter, with costs dominated by hardware depreciation rather than electricity. Under typical usage, Apple Silicon can cost around three times more per million tokens compared to OpenRouter, which also offers faster inference speeds. Despite higher costs and slower performance, consumer devices like the M5 MacBook Pro can still run models approaching the performance level of advanced cloud-based systems.
- ▪Apple Silicon inference costs are dominated by hardware depreciation, with electricity costing only about $0.02 per hour at full load.
- ▪A 64GB M5 MacBook Pro running Gemma 4 31B locally may cost $0.40 to $4.79 per million tokens depending on lifespan and performance.
- ▪OpenRouter offers comparable models at roughly $0.38 to $0.50 per million tokens and with speeds up to 60-70 tokens per second, significantly faster than local inference on Apple Silicon.
- ▪For most users, cloud-based inference via services like OpenRouter is both cheaper and faster than running models locally on Apple Silicon.
- ▪Employee salary costs for using local AI inference are approximately 1,000 times higher than the token generation cost, making cloud solutions more economically sensible.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Williamangel |
| Canonical URL | https://www.williamangel.net/blog/2026/05/17/offline-llm-energy-use.html |
| Publication time | Sun, 17 May 2026 12:09:23 +0000 |
| Retrieval time | 2026-05-17T12:22:13.120Z |
| Last seen | 2026-05-17T12:22:13.120Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 2_GsWMzSedPW |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Offline Agentic Coding part 3: Apple Silicon costs more than OpenRouter. Published 2026-05-17 Apple silicon costs more than OpenRouter. At ~50-100 watts under load, and ~$0.20 per kWh, my M5 MacbookPro will cost a few cents per hour. Accelerated depreciation (if any) from shortening the lifespan of the device will be more expensive than the electricity. At a few tens of tokens per second this works out to ammortized costs of ~$1.50 per million tokens. Openrouter for comparable models is 1/3rd the price and ~2x the speed. Electricity In Northern Virginia my last electricity bill worked out to $0.18 per kilowatt hour. Let's round up to $0.20 per kWh. EIA has average residential costs for 2025 at $0.1730 per kWh in the US.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Williamangel.
Discussion
0 commentsMore from Williamangel
