MatX
High-throughput chips for LLMs
Mountain View, United States · Founded 2023 · $600.0M raised
- Headquarters
- Mountain View, California
- Employees
- 11–50
- Founded
- 2023
- Business Model
- B2B
- Website
- matx.com
- Total Funding
- $600.0M
- Last Round
- $500.0M Series BFeb 2026
- Rounds
- 2
About
MatX designs high-throughput AI chips purpose-built for large language model training and inference. Founded by former Google TPU architects, the company's MatX One chip targets frontier AI labs with industry-leading FLOPS per mm², SRAM-resident weights for ultra-low latency, and massive scale-out interconnect supporting hundreds of thousands of chips. MatX raised a $500M Series B in February 2026 to accelerate chip production.
Summary
MatX is an Artificial Intelligence company based in Mountain View, United States, founded in 2023. It has raised $600.0M in total across 2 rounds, most recently a $500.0M Series B round in Feb 2026. Investors include Jane Street, Spark Capital and Situational Awareness.
Tech & App Stack
4 technologies & apps tracked
Create a free account — 10 credits a month to unlock the full tech & app stack, funding history, and valuations.
Sign up to view the funding chart
Create a free account — you'll get 10 credits a month to unlock funding history, valuations, and tech stacks.
Funding History
Feb 2026
Sign up to see all 2 rounds
Full funding history, per-round amounts, and investor participation.
Investors
Similar Companies
Groq delivers fast, low cost AI inference using custom LPU (Language Processing Unit) chips and G...

AI hardware company building wafer-scale processors for deep learning training and inference
Provides AI inference hardware and cloud platform for enterprises, using RDUs and SambaCloud to r...
Designs and sells AI processors, accelerator cards, and software, licensing RISC-V IP to enterpri...

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artifi...
Anthropic is an AI research company that builds reliable, interpretable, and steerable AI systems.
