# \#performance

**URL:** https://forum.modular.com/tag/performance/23.md

[Latest](https://forum.modular.com/latest.md) · [Categories](https://forum.modular.com/categories.md) · [Tags](https://forum.modular.com/tags.md)

---

## [Bare-metal Mojo on a $4 microcontroller — a pure-Mojo RP2040 firmware + SDK](https://forum.modular.com/t/bare-metal-mojo-on-a-4-microcontroller-a-pure-mojo-rp2040-firmware-sdk/3298)

<div class="topic-metadata">

**Author:** [@Hundo](https://forum.modular.com/u/Hundo)\
**Replies:** 21\
**Last updated:** [October 19, 2026, 10:07pm UTC](https://forum.modular.com/t/bare-metal-mojo-on-a-4-microcontroller-a-pure-mojo-rp2040-firmware-sdk/3298 "2026-10-19T22:07:07Z")

</div>

Mojo is usually pointed at GPUs and AI kernels. I wanted to see how far the other direction goes, so I wrote a bare-metal firmware and peripheral SDK for the Raspberry Pi Pico (RP2040, a dual Cortex-M0+) in pure Mojo — n…

---

## [MXFrame: Cross-vendor GPU DataFrames with Mojo AOT kernels](https://forum.modular.com/t/mxframe-cross-vendor-gpu-dataframes-with-mojo-aot-kernels/3358)

<div class="topic-metadata">

**Author:** [@abhisheksreesaila](https://forum.modular.com/u/abhisheksreesaila)\
**Replies:** 6\
**Last updated:** [July 31, 2026, 7:51pm UTC](https://forum.modular.com/t/mxframe-cross-vendor-gpu-dataframes-with-mojo-aot-kernels/3358 "2026-07-31T19:51:42Z")

</div>

Hey everyone :waving\_hand: A 6-table join over 10 million rows in 0.7 ms. That’s 128× faster than Polars — and it’s running on hand-written Mojo kernels with zero CUDA anywhere in the stack. I’ve been building MXFrame:…

---

## [Custom MultiHead Self Attention Transformer Training Phase using AMD RX 9070 XT 16GB. Python/Pythorch Vs Mojo](https://forum.modular.com/t/custom-multihead-self-attention-transformer-training-phase-using-amd-rx-9070-xt-16gb-python-pythorch-vs-mojo/2633)

<div class="topic-metadata">

**Author:** [@Andrea](https://forum.modular.com/u/Andrea)\
**Replies:** 6\
**Last updated:** [February 7, 2026, 4:57pm UTC](https://forum.modular.com/t/custom-multihead-self-attention-transformer-training-phase-using-amd-rx-9070-xt-16gb-python-pythorch-vs-mojo/2633 "2026-02-07T16:57:48Z")

</div>

I wrote a program in python that uses the pytorch package that performs the four steps to build an LLM and use it. Preparation of the data corpus. Training on unsupervised data (wikipedia dump). Training on supervised …

---

## [Llama2.🔥 performance degradation after updating code to the latest Mojo compiler](https://forum.modular.com/t/llama2-performance-degradation-after-updating-code-to-the-latest-mojo-compiler/2465)

<div class="topic-metadata">

**Author:** [@Aydyn](https://forum.modular.com/u/Aydyn)\
**Replies:** 1\
**Last updated:** [November 21, 2025, 8:58pm UTC](https://forum.modular.com/t/llama2-performance-degradation-after-updating-code-to-the-latest-mojo-compiler/2465 "2025-11-21T20:58:14Z")

</div>

Hi everyone. I haven’t touched my llama2.:fire: github repo for a long time. More precisely since March 2024 I have finally refactored this legend today. Mojo compiler ver is 0.25.7.0 https://github.com/tairov/llama2.…

---

## [Mojo vs max mandelbrot performance](https://forum.modular.com/t/mojo-vs-max-mandelbrot-performance/1429)

<div class="topic-metadata">

**Author:** [@eshishkin](https://forum.modular.com/u/eshishkin)\
**Replies:** 5\
**Last updated:** [May 12, 2025, 3:51pm UTC](https://forum.modular.com/t/mojo-vs-max-mandelbrot-performance/1429 "2025-05-12T15:51:07Z")

</div>

I decided to compare mandelbrot performance in plain mojo modular/examples/mojo/mandelbrot.mojo at main · modular/modular · GitHub and in max modular/examples/custom\_ops/mandelbrot.py at main · modular/modular · GitHub …