Skip to content

Beta: real launches, updated every morning. Rankings may change while we tune them.

llama-modchip

πŸ‹ Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.

112Rank on 17 November 2026Up 8 places from 16 Nov

llama-modchip launched on 29 October 2026. It ranked #112 on Daily Launch on 17 November 2026 with a Launch Score of 11, from +39 stars on 17 Nov on GitHub. It moved up 8 places from the day before.

Visit site39 stars on GitHub on 17 Nov
Share

What is Llama Modchip?

Submit your terminal scorecard via a GitHub Benchmark Issue or GitHub Discussions to add your CPU to the leaderboard below.

From its README on GitHub

Llama Modchip (llama-modchip) is a repo by synchopate on GitHub. It is written in Python and released under the Apache-2.0 license.

How to get Llama Modchip

curl -sL https://raw.githubusercontent.com/synchopate/llama-modchip/main/install.sh | bash

From its README on GitHub

More steps and the source are in its repository on GitHub.

Daily Launch card for llama-modchip

In its own words

Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).

From its GitHub repository

Launch timeline

  1. GitHubRepository created

  2. GitHub809 stars in 12 days, ranked #93 on Daily Launch

  3. GitHub+107 stars, ranked #127 on Daily Launch

  4. GitHub+34 stars, ranked #107 on Daily Launch

  5. GitHub+196 stars, ranked #47 on Daily Launch

  6. GitHub+58 stars, ranked #84 on Daily Launch

  7. GitHub+45 stars, ranked #101 on Daily Launch

  8. GitHub+37 stars, ranked #120 on Daily Launch

  9. GitHub+39 stars, ranked #112 on Daily Launch

Launch Score, last 7 days

05010011 Nov: 2011 Nov12 Nov: 312 Nov13 Nov: 3913 Nov14 Nov: 2214 Nov15 Nov: 1315 Nov16 Nov: 616 Nov17 Nov: 1117 Nov11 17 Nov
Launch Score, 0 to 100. Days it was not ranked show 0.