DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Whallm: what you can do with it

What is Whallm? Whallm is a macOS app that runs large language models on Apple Silicon Macs by keeping common weights in memory and reading experts from SSD, with a chat interface and an OpenAI-compatible API server.

How do I use it? Download Whallm-macOS-arm64.zip from GitHub Releases, unzip it and open Whallm.app; then open Model, pick a model and select Download Model. Wait for the download to finish, resuming it if it stops; open Server and select Start Server. The default address is http://127.0.0.1:11434. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Point Codex at a local model on your Mac

    Run Whallm's server on your Mac and send Codex requests to it instead of a hosted API.

    View prompt
    Work in the Whallm repo at yanun0323/Whallm. Confirm the Whallm server is running at http://127.0.0.1:11434 and that GET /v1/models lists the model ID <model-id>. Then check that ~/.codex/config.toml sets model_provider to deepseek-v4-ssd with base_url http://127.0.0.1:11434/v1 and wire_api set to responses, and report whether the file matches the README example.

  • Chat with a large model privately on your Mac

    Use Whallm's built-in Chat window to ask a large local model questions without a hosted service.

    View prompt
    In the Whallm repo at yanun0323/Whallm, check the README's Supported models table and the Requirements section against this Mac's chip, macOS version, memory and free disk space for <model-name>. Report whether the model fits and which steps from the Quick start remain.

  • Measure which local model runs well on your Mac

    Use the Throughput tool to test prefill and decode speed on your own hardware before committing to a large download.

    View prompt
    In the yanun0323/Whallm repo, read the Benchmark summary and the BENCHMARK.md file and list the metrics and settings a user must record to compare a run with the published results. Output a short checklist with the chip, cache mode, slots, prefill, decode and peak memory, and note that the README calls these numbers reference only.

  • Call the local model from a script through its API

    Send requests from your own code to Whallm's OpenAI-compatible endpoint running on your Mac.

    View prompt
    In the yanun0323/Whallm repo, read the README sections on the API and Connect Codex, then write a short script that calls GET /v1/models at http://127.0.0.1:11434 and prints each API model ID. Run it against a running Whallm server, and verify that the printed IDs match the model ID table in docs/usage.md.

Quick start with Whallm

  1. Check you have what it needs: Apple Silicon Mac running macOS 15 or later; 64 GiB memory recommended, with more disk space than the chosen model's files (Qwen models about 118 to 119 GiB, DeepSeek V4.1 above 458 GiB); Fast internal, Thunderbolt or USB4 SSD.
  2. Open yanun0323/Whallm on GitHub and read the README and license.
  3. Download Whallm-macOS-arm64.zip from GitHub Releases, unzip it and open Whallm.app.
  4. Open Model, pick a model and select Download Model. Wait for the download to finish, resuming it if it stops.
  5. Open Server and select Start Server. The default address is http://127.0.0.1:11434.
  6. Add the provider block from the README to ~/.codex/config.toml, setting model to an API model ID such as deepseek-v4-flash-0731 or an Alias you set in Model to Advanced Settings.

These steps come from our top use case, Point Codex at a local model on your Mac, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for yanun0323/Whallm

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Whallm alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forMac users on Apple Silicon with fast storage and enough disk space who want to run large local models for chat or as a local API for clients like Codex.
  • Why it is hot151 stars, launched 80 days ago
  • LanguagePython
  • Sourcegithub.com/yanun0323/Whallm · Back to Hot repos

Requirements

  • Apple Silicon Mac running macOS 15 or later
  • 64 GiB memory recommended, with more disk space than the chosen model's files (Qwen models about 118 to 119 GiB, DeepSeek V4.1 above 458 GiB)
  • Fast internal, Thunderbolt or USB4 SSD
  • Network access to download the Whallm release and model weights

Add this badge to your README

Maintain Whallm? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/yanun0323/Whallm.svg)](https://dedupedai.com/use-cases/yanun0323-whallm/?utm_source=github&utm_medium=badge&utm_campaign=yanun0323-Whallm)

HTML 

<a href="https://dedupedai.com/use-cases/yanun0323-whallm/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=yanun0323-Whallm"><img src="https://dedupedai.com/badge/yanun0323/Whallm.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Whallm

What is Whallm?

Whallm is a macOS app that runs large language models on Apple Silicon Macs by keeping common weights in memory and reading experts from SSD, with a chat interface and an OpenAI-compatible API server. It is an open-source project on GitHub: https://github.com/yanun0323/Whallm.

How do I use Whallm?

Download Whallm-macOS-arm64.zip from GitHub Releases, unzip it and open Whallm.app; then open Model, pick a model and select Download Model. Wait for the download to finish, resuming it if it stops; open Server and select Start Server. The default address is http://127.0.0.1:11434. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Whallm for?

Mac users on Apple Silicon with fast storage and enough disk space who want to run large local models for chat or as a local API for clients like Codex.

What can I do with Whallm?

4 use cases so far, for example: Point Codex at a local model on your Mac; Chat with a large model privately on your Mac; Measure which local model runs well on your Mac. Each has steps and a copy-paste agent prompt.

What do I need to run Whallm?

Apple Silicon Mac running macOS 15 or later; 64 GiB memory recommended, with more disk space than the chosen model's files (Qwen models about 118 to 119 GiB, DeepSeek V4.1 above 458 GiB); Fast internal, Thunderbolt or USB4 SSD; Network access to download the Whallm release and model weights.

What are alternatives to Whallm?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Whallm safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.