Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Busbar
Busbar
Omnigraph
Omnigraph
OfinTech Desk
OfinTech Desk
Bifrost
Bifrost
It's a plan
It's a plan

ArneshBanerjee/gpt2.s

GPT-2 small (124M) in hand-written AArch64 assembly. No libc calls. About 100 tokens/s on an M1.

#LLM inference
Visit GitHub
Assembly
105
11
1 contributors
MIT License
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Momentum

How fast ArneshBanerjee/gpt2.s is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Nov 6 – Nov 19, 2026

Stars +105 in 14 days

050100
62

Forks +11 in 14 days

0510
7

Merged PRs 6 in 14 days

012
2

Trendshift Trendingwhere the repository ranked each day it made the top 25

Top 25 in Assembly

211511
Nov 6Nov 8Nov 10Nov 12Nov 14Nov 16Nov 18
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRsAssembly
Fri, Nov 6, 2026+0+00Not trending
Sat, Nov 7, 2026+22+32#2
Sun, Nov 8, 2026+62+71#1
Mon, Nov 9, 2026+4+02#15
Tue, Nov 10, 2026+5+01#11
Wed, Nov 11, 2026+2+10Not trending
Thu, Nov 12, 2026+3+00Not trending
Fri, Nov 13, 2026+2+00Not trending
Sat, Nov 14, 2026+1+00Not trending
Sun, Nov 15, 2026+0+00Not trending
Mon, Nov 16, 2026+2+00Not trending
Tue, Nov 17, 2026+1+00Not trending
Wed, Nov 18, 2026+0+00Not trending
Thu, Nov 19, 2026+1+00Not trending
Total+105+116
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Mentions and achievements

Where people are talking about ArneshBanerjee/gpt2.s, and every badge it has earned
    1. Nov 72 posts
      • i built gpt-2 in pure assembly. 124m params. zero libc calls. the tokenizer, matmuls, attention, softmax, even exp(): all arm64 asm. ~100 tok/s on a single m1 core. 4 kb of machine code. output…

        Read full on X, posted by @Arnesh_24

        @Arnesh_24 · x.com

      • gpt-2 in css runs at 15 sec/tok. so i went the other way. gpt-2 (124m) in hand-written arm64 assembly. zero libc calls, only raw syscalls. tokenizer, matmuls, softmax, exp: all asm. 103 tok/s on one…

        Read full on X, posted by @Arnesh_24

        @Arnesh_24 · x.com

    You might also like

    Repositories close to ArneshBanerjee/gpt2.s
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    Busbar

    Control what AI can do before it acts

    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    Entrpi/eemicrogpt

    C

    The most extreme way to train a GPT in pure, dependency-free C. 84000x faster than Python. Optimized for Apple Silicon with SME2.

    698

    rayl15/Godwit

    Swift

    Run GPT-OSS-120B on a 16 GB Mac. Streams mixture-of-experts weights from SSD so only the 2 GiB trunk stays resident. Swift + Metal, no dependencies.

    252

    nektarlabs/inferno

    Rust

    Inferno aims to be a super lightweight, highly efficient Rust inference engine for running open weights models on Apple Silicon with Metal, targeting machines such as a MacBook Pro with 64 GB of unified memory.

    456

    drumih/turbo-fieldfare

    Swift

    Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

    7.4k530

    ml-explore/mlx-lm

    Python

    Run LLMs with MLX

    7.7k1.2k

    torinriley/alpaca

    Swift

    Swift-native LLM inference engine for Apple Silicon

    222

    mmastrac/diffgemma

    Rust

    A pure Rust implementation of Google's DiffusionGemma model

    375

    jaymody/picoGPT

    Python

    An unnecessarily tiny implementation of GPT-2 in NumPy.

    3.5k466

    NeelM0906/Mference

    Swift

    Swift + Metal MoE inference for Apple Silicon: Qwen 3.6 35B at 23.5–29.3 tok/s decode with 2.20× faster long-prompt prefill on a 24 GB M5; Gemma 4 26B in ~2 GB, DeepSeek-V4-Flash 284B, Inkling-Small 276B, native Mac app, CLI, and OpenAI-compatible server.

    12321