First Gemma 4 ExecuTorch Deployment on Raspberry Pi 5 — and Why It's 7.7 Slower Than llama.cpp

May 25, 2026 · 11:19 AM UTC ·5 min read · 0 reactions · 0 comments · 42 views

#executorch #edgeai #raspberrypi #gemma4

TL;DR · WeSearch summary

The first deployment of Gemma 4 ExecuTorch on a Raspberry Pi 5 has been documented, revealing significant performance differences compared to ARM's benchmarks. The deployment achieved bit-exact output but was found to be 7.7 times slower than llama.cpp. Various issues were encountered during the process, highlighting the challenges of deploying on non-SME2 hardware.

Key facts

▪Gemma 4 was optimized for ARM devices, achieving notable speed improvements on flagship chips.
▪The deployment on Raspberry Pi 5 resulted in a decode speed of 0.87 tokens per second, significantly slower than the 6.71 tokens per second achieved by llama.cpp.
▪The performance gap is attributed to issues with kernel fusion in the ExecuTorch XNNPACK backend on aarch64 systems.

About this source

DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.

All DEV.to (Top) coverage →

Original article

DEV.to (Top)

Read full at DEV.to (Top) →

Story provenance

Source · retrieval · rights · ranking — open for full record

inspect →

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	DEV.to (Top)
Canonical URL	https://dev.to/bamb00boy/first-gemma-4-executorch-deployment-on-raspberry-pi-5-and-why-its-77x-slower-than-llamacpp-gmb
Publication time	Mon, 25 May 2026 11:19:02 +0000
Retrieval time	2026-05-25T11:37:36.700Z
Last seen	2026-05-25T11:37:36.700Z
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	q70QMW0hy0FX
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)

Publisher-declared

No publisher-confirmed rights record for this source yet.

Machine-readable

No source-specific machine-readable restriction detected beyond the public feed.

WeSearch interpretation

WeSearch declared handling (basis: Derived from the published RSS/Atom feed). This is WeSearch policy, not a legal grant on the publisher's behalf.

Unknown

Retrieval and training permissions are not asserted unless the publisher confirms them.

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.

Open original publisher → Source rights JSON → Machine-readable provenance → Rights framework → WESEARCH-STORY-PROVENANCE-V1

Opening excerpt (first ~120 words) tap to expand

try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3950536) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Viik Posted on May 25 First Gemma 4 ExecuTorch Deployment on Raspberry Pi 5 — and Why It's 7.7 Slower Than llama.cpp #executorch #edgeai #raspberrypi #gemma4 On April 2, ARM published a blog post announcing Gemma 4 optimised for ARM devices via XNNPACK + KleidiAI, reporting 5.5× prefill speedup and 1.6× faster decode. Those numbers target Armv9 chips with SME2 — flagship phone silicon. I wanted to see what happens on the broader ARM ecosystem.

…

Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).

Anonymous · no account needed

Discussion

0 comments