antirez/ds4

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

DwarfStar aims to be the best way to run a few excellent large language models on consumer hardware (that is, hardware that people can actually own). To reach this goal, we are building a small native inference engine optimized first for DeepSeek V4 Flash (including the experimental vision model), DeepSeek V4.1 Flash (Metal, and text inference on CUDA), and additionally GLM 5.2 and 5.3, GLM 5.3 Flash and DeepSeek V4 PRO, and Qwen3.8 Flash Next (Metal and CUDA). The code is self-contained and deliberately narrow, not a general GGUF runner: you need to use the GGUF files the project produces, that are part of the project itself. We test things in integration: model loading, prompt rendering, tool calls, KV state, the HTTP server, and the coding agent are built and tested together. The repository also includes tools and data for GGUF, imatrix, quality, and speed. This project would not exist…

antirez/ds4 on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-11-13T20:30:44.847Z

Inside the original README — Document outline
  1. Supported hardware
  2. So, what can I do with this software?
  3. Motivations
  4. AI full disclosure
  5. Acknowledgements to llama.cpp and GGML
  6. Status
  7. How to use this project?
  8. Start Here
  9. Everyday Use
  10. Native coding agent
  11. Models, images, and speculation
  12. Output and power

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Repository facts

Owner
antirez
Primary language
C
Stars
23,267
Forks
2,239
Open issues + pull requests
757
License
MIT
Archived
No
Default branch
main
Created
2026-05-06T17:17:05.000Z
Last push
2026-09-20T07:51:19.000Z

Topics and intended use

No topics were included in the latest source metadata.

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-10-04T12:03:43.929Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

torvalds/linux

Genymobile/scrcpy

microsoft/PowerToys

colbymchenry/codegraph

git/git

DeusData/codebase-memory-mcp