# Gemma 4 26B inference engine for Mac

15 Hacker News commenters recommended Gemma 4 26B inference engine for Mac and 2 criticized it, November 2025 to November 2026. It was recommended in 1 of 13 months.

**Verdict:** Free open-source engine that runs Gemma 4 26B in about 2 GB of RAM on M-series Macs. Critics say generation is too slow on some Macs.

## Why people recommend it

- Usable token speeds on Apple Silicon (4 comments): "Got 48 tok/s decode at 1.9 GB RSS (2.4 GB peak), faster than the 24 GB M5 Pro mentioned in the benchmarks." ([source](https://news.ycombinator.com/item?id=49107305)) "12 tok/s and almost instant response in M1 Max Mac Studio (with faster SSD than laptops) are impressive" ([source](https://news.ycombinator.com/item?id=49100842)) "I tried it on my wife's M1 MacBook Air 512GB and it gets 4–5 tok/s" ([source](https://news.ycombinator.com/item?id=49098975))
- Large model runs in 2 GB RAM (2 comments): "Got 48 tok/s decode at 1.9 GB RSS (2.4 GB peak), faster than the 24 GB M5 Pro mentioned in the benchmarks." ([source](https://news.ycombinator.com/item?id=49107305)) "seeing 14GB of weights crammed into 2GB of RAM is impressive." ([source](https://news.ycombinator.com/item?id=49099145))
- Impressive, does what it says (2 comments): "It does exactly what it says it does." ([source](https://news.ycombinator.com/item?id=49099217)) "Tried it and i'm impressed." ([source](https://news.ycombinator.com/item?id=49120357))

## What people warn about

- Too slow on some Macs (2 comments): "the token generation rate is simply far too low" ([source](https://news.ycombinator.com/item?id=49105421)) "I'm only getting < 1 token/second on my Neo" ([source](https://news.ycombinator.com/item?id=49114509))

## Alternatives hackers recommend

- [vLLM](https://hackerapproved.com/p/vllm.md): 112 recommend
- [Strata](https://hackerapproved.com/p/strata.md): 31 recommend
- [DwarfStar 4](https://hackerapproved.com/p/dwarfstar.md): 26 recommend
- [SGLang](https://hackerapproved.com/p/sglang.md): 19 recommend
- [ninfer](https://hackerapproved.com/p/ninfer.md): 16 recommend

## Cite as

Hacker Approved, "Gemma 4 26B inference engine for Mac", https://hackerapproved.com/p/open-source-engine-running-gemma-4-26b-on-m-series-mac/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).