---
schema: 1
type: video
title: >-
  Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin,
  Locally AI
description: >-
  See more: https://x.com/adrgrondin/status/2040512861953270226 Speaker info: -
  https://x.com/adrgrondin --- Watch along with the corrected transcript,
  summary, timestamps and resources on this talk's official AIE page:
  https://ai.engineer/talks/a2muGkT4WD4-running-gemma-4-on-device-40-tokens-s-on-iphone-with-mlx
  Join our upcoming AI Engineer conferences (see https://ai.engineer landing
  page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs
  and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference
  returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS
  2026 in Sydney ---
canonical: 'https://liquidgold.cc/watch/a2muGkT4WD4'
markdown: 'https://liquidgold.cc/watch/a2muGkT4WD4.md'
llms: 'https://liquidgold.cc/watch/a2muGkT4WD4/llms.txt'
parent: 'https://liquidgold.cc/channel/aidotengineer.md'
channel: aidotengineer
updated: '2026-10-24T15:10:21.307Z'
language: null
children: []
videoId: a2muGkT4WD4
durationSeconds: 651
publishedAt: '2026-04-20T21:53:25.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 26
    endSeconds: 104
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=26'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 26
    endSeconds: 104
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=26'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 115
    endSeconds: 214
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=115'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 115
    endSeconds: 214
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=115'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 214
    endSeconds: 225
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=214'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 225
    endSeconds: 351
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=225'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 351
    endSeconds: 361
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=351'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 361
    endSeconds: 467
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=361'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 467
    endSeconds: 478
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=467'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 478
    endSeconds: 567
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=478'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 567
    endSeconds: 578
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=567'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 225
    endSeconds: 351
    watch: 'https://liquidgold.cc/watch/a2muGkT4WD4?t=225'
    heldReason: rights
---


# Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI

See more: https://x.com/adrgrondin/status/2040512861953270226 Speaker info: - https://x.com/adrgrondin --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/a2muGkT4WD4-running-gemma-4-on-device-40-tokens-s-on-iphone-with-mlx Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney ---

Canonical: https://liquidgold.cc/watch/a2muGkT4WD4 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.