deltafin
Deltafin runs the full, unpruned Kimi K3 locally and provides an OpenAI-compatible API for chat and coding agents. It explores local inference on consumer hardware without reducing model quality.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XCustom license (see repository)
Overview
Deltafin is a Rust project packaged as a native binary for running the complete, unpruned 2.8-trillion-parameter Kimi K3 model on a single device. It explores local inference for a model intended for large-scale infrastructure while keeping all 16 experts and leaving token decisions to K3. Optional small draft models can propose tokens, which K3 verifies. The project also provides an OpenAI-compatible API server for local chat and coding agents, with support listed for macOS ARM64 and Linux x86-64/aarch64 using Metal/MPS, CUDA, or CPU.
Key features
- Runs the full, unpruned Kimi K3 model with all 16 experts.
- Lets optional small draft models suggest tokens, then has K3 verify them.
- Provides an OpenAI-compatible API server for local chat and coding agents.
- Lists macOS ARM64 and Linux support with Metal/MPS, CUDA, or CPU.
Best for
Researchers and enthusiasts exploring how to run a very large model locally without pruning it. It also suits people who want an OpenAI-compatible local API for chat or coding agents.
- Upstream
- gavamedia/deltafin
- Fork on GitHub
- Guo-astro/deltafin
- Upstream stars
- 857
- Category
- AI agents and LLM tools
- License
- Custom license (see repository)
- Forked
- 2026-10-13
- Sync status
- In syncLast synced 2026-11-08
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub