Zapdev-labs

Zapdev-labs

Building faster LLMs on real hardware

Zapdev-labs builds quantization, inference runtimes, and benchmarks — Rust and Python tooling that cuts memory, raises tokens-per-second, and ships local /v1 chat HTTP APIs you can run on your hardware.

Contact meView projects

Current Focus

LLM Compression

Weight and KV-cache quantization — PolarQuant, FastVQ, and oxidize-quantize for edge deployment.

GitHubHugging Facezapdev.link

Local Inference

Rust and Python runtimes with drop-in /v1 chat endpoints — oxidize, turboforge, and miniforge.

Open Source

Benchmarks, agent tooling, and inference stacks built in public for developers worldwide.

12+
Open-source projects
3-bit
KV cache compression
6×
KV memory reduction

Open Source Work

Tools and libraries built in public.

View all on GitHub
Rust

oxidize

Fast, local-first LLM inference in Rust — CLI, /v1 chat HTTP server, and Python bindings.

oxidize— stars
Python

turboquant

Near-optimal KV cache quantization with FastVQ — ~3-bit keys, ~6× smaller caches, GPU kernels.

turboquant— stars
Python

turboforge

Hardware-aware enterprise runtime with a llama.cpp backend plus benchmark telemetry.

turboforge— stars
Python

miniforge

High-performance MiniMax inference with GGUF quantization and TurboQuant KV modes.

miniforge— stars
Python

ollama-performance-benchmark

Back-to-back TPS benchmark on one GGUF — oxidize and miniforge vs stock llama.cpp.

ollama-performance-benchmark— stars
TypeScript

openagentmail

Self-hosted AgentMail-compatible email for AI agents — inboxes, threads, and webhooks.

openagentmail— stars

Selected Capabilities

We take on complex inference problems at the edge of what's possible and make them boringly reliable.

AI / INFERENCE

LLM infrastructure, quantization pipelines, and local serving stacks.

DEV TOOLS

Open-source libraries, hardware probes, and cross-backend benchmark harnesses.

PRODUCT / SYSTEMS

Interfaces and APIs that match the depth of the underlying inference system.

Recent Work

What we've been building lately

All projects
Open Source

oxidize

Rust-native local LLM inference

Open Source

turboquant

KV cache quantization for LLM inference

Open Source

turboforge

Hardware-aware inference runtime

Open Source

miniforge

MiniMax serving with TurboQuant KV

Built With

llama.cppGGUFRustTritonConvexE2BHugging FacePyTorchMiniMaxOllamaoxidizellama.cppGGUFRustTritonConvexE2BHugging FacePyTorchMiniMaxOllamaoxidize

Install

One command to run models locally

The installer detects your OS and architecture, drops the oxidize binary on your PATH, and falls back to a source build when no prebuilt is published. macOS, Linux, and Windows — x86_64 and arm64.

$ curl -fsSL https://zapdev.link/install.sh | sh

Cargo

From source, any platform

cargo install --git https://github.com/Zapdev-labs/oxidize --bin oxidize --locked

wget

No curl? No problem

wget -qO- https://zapdev.link/install.sh | sh

Piping to a shell runs code from the network. Read it first: zapdev.link/install.sh

How we work

Issue in, fix out

Most work starts on oxidize — open a GitHub issue, research the root cause, then use AI tooling to land a tested patch.

  1. 01

    Open an issue

    File a repro on oxidize — crash, wrong output, or slow inference

  2. 02

    Research

    Read the stack trace · profile on real hardware · trace root cause

  3. 03

    AI-assisted fix

    Cursor on the oxidize codebase · patch, test, open PR

Proof, not promises

Benchmarks you can rerun

ollama-performance-benchmark runs each backend sequentially on the same GGUF and prompt. On our hardware, oxidize and miniforge beat stock llama.cpp tokens-per-second.

View benchmark repo
ollama-performance-benchmark · results.csvtok/s
llama.cppsame GGUF
oxidizefastest
miniforgesame GGUF
Ollamasame GGUF

Back-to-back run on one prompt · Ryzen 7 PRO · Qwen3.5-4B Q4

Reference

Common questions

We are a machine learning lab focused on LLM performance: quantization (turboquant), local inference stacks (oxidize, miniforge, turboforge), and honest cross-backend benchmarks. We also ship agent infrastructure like openagentmail and product tooling like zapdev.

Stay Updated

Reach out for collaboration on quantization, local inference, or benchmark work.

Jacksonwheeler@zapdev.linkContact