ZML releases free cross-chip AI inference tool
Paris-based startup ZML has released a free tool for cross-chip inference of open AI models. It runs fast on Nvidia, AMD, Google, Apple and Intel hardware, which helps loosen Nvidia's grip on AI hardware. It is a software fix, not a hardware one, for breaking out of the Nvidia lock-in.
AI-processed from TNW; edited by Hamidun News
# ZML: a free tool against Nvidia lock-in
On July 14, 2026, Paris startup ZML unveiled a free tool aimed at one of the AI industry's key problems: dependence on Nvidia hardware.
The problem: Nvidia lock-in
Today Nvidia dominates the market for AI processors and graphics cards:
- Most models are optimized for Nvidia
- Tools and frameworks usually run better on Nvidia
- This creates a vendor lock-in effect
ZML's solution
Instead of developing new hardware, ZML built a software solution:
- A free tool for model inference
- Optimizes performance on Nvidia, AMD, Google, Apple and Intel
- Works with open models
- Achieves high speed on a variety of hardware
Strategy
ZML's approach focuses on software, not hardware. The barrier to entry is lower than competing with Nvidia in hardware.
What it means
Nvidia's hold on the AI ecosystem is starting to thin thanks to software innovation. ZML shows that it is possible to build competitive solutions through smart software rather than hardware competition.
- Nov 1, 2026Google taught its StreamVibe video agent to decide when to step in on its own: +10.7%
- Nov 1, 2026OpenAI Rewrites GPT Behavior Rules: Five Values and a Chain of Command
- Nov 1, 2026Voice bots built on LLMs turn to Jev, a fast classifier, for decisions in 200–500 ms
- Nov 1, 2026Google admits AI Mode cuts search revenue, shares fall 15%
Key Questions Answered
What are the key details on The problem: Nvidia lock-in?
Today Nvidia dominates the market for AI processors and graphics cards: Most models are optimized for Nvidia Tools and frameworks usually run better on Nvidia This creates a vendor lock-in effect
What are the key details on ZML's solution?
Instead of developing new hardware, ZML built a software solution: A free tool for model inference Optimizes performance on Nvidia, AMD, Google, Apple and Intel Works with open models Achieves high speed on a variety of hardware
What are the key details on Strategy?
ZML's approach focuses on software, not hardware. The barrier to entry is lower than competing with Nvidia in hardware.
Ship AI Faster with Founders, Engineers & Weekly Architecture Reviews
Inside Vibe Club (hamidun.com/club) — weekly live masterminds with Zhemal Khamidun, Tech Radar, full LMS access, and 370+ production Claude Code skills.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.