Axelera AI vs Tenstorrent
Relationship
Axelera Metis AIPU and Blackhole do comparable work on accelerator silicon; both also serve buyers who need to buy data-centre AI compute; same layer and the same scale band (growth-stage private).
Assembled from the recorded fields for this pair, not hand-checked. The comparison below is read from each company’s own profile.
3 of 3 capabilities — Shares AI compute hardware, accelerator silicon and model inference.
Ludbee capability tags · from the product recordsShared product type — Both ship hardware.
Ludbee product recordsSame scale band — Both growth-stage private.
Ludbee scale bands · from valuation and funding figuresAligned comparison
Capability overlap
Shared · 3
Not verified for Axelera AI · 3
Recorded for Tenstorrent. Axelera AI’s product records say nothing either way — a missing record is not a missing capability.
Axelera AI has no capability Tenstorrent lacks, among the 3 recorded here.
Products, side by side
Algorithmic pairing — assembled from recorded fields, not hand-checked
Axelera AI
Hardware
Compact NUC-form-factor edge AI system pairing an Intel Core Ultra 5 125H with an Axelera Embedded 113m accelerator (214 TOPS, 250+ TOPS combined), 32GB DDR5, 256GB NVMe, running Ubuntu 24.04 with the Voyager SDK.
Single-board computer for multi-stream computer-vision and generative-AI edge inference: quad-core Metis AIPU paired with an ARM RK3588, 16GB LPDDR4 for the CPU plus 4GB or 16GB LPDDR4X for the accelerator.
Edge AI accelerator sold as PCIe cards and modules for running computer-vision models on site.
Next-generation AI accelerator chip (629 TOPS, 8 second-generation AI processing cores, 16 RISC-V vector cores) extending Axelera's edge AI beyond ultra-low-power devices into enterprise-server, multi-user generative AI, robotics and automotive use cases.
Tenstorrent
Hardware
RISC-V-based AI accelerator sold as standalone PCIe developer cards (Blackhole p100a, p150a, p150b) alongside the previous-generation Wormhole boards on Tenstorrent's card catalogue page.
High-performance RISC-V CPU core licensed as silicon IP to chip designers for use in AI accelerators, chiplets and custom SoCs.
Air-cooled desktop AI workstation built around four Tenstorrent Wormhole n300s cards (eight Tensix processors) with a 96GB expandable memory pool, sold for local AI model development and HPC library porting.
Liquid-cooled desktop AI workstation containing four Tenstorrent Tensix processors, an AMD Ryzen CPU, DDR5 memory and NVMe storage, sold for running and developing AI models locally.
AI accelerator core licensed as silicon IP to chip designers for embedding Tenstorrent's Tensix compute into their own SoCs and chiplets.
Rack-mount AI compute server built from 32 Tenstorrent Tensix processors with built-in Ethernet scale-out, sold in Blackhole and Wormhole generations and in multi-server supercluster configurations.
No counterpart
Axelera AI sells these in a stack layer with no product recorded for Tenstorrent yet — nothing on the other side to compare them against.
Developer tool
Toolchain that compiles and deploys models onto Axelera accelerators, with a model zoo and pipeline tools.
Tenstorrent sells these in a stack layer with no product recorded for Axelera AI yet — nothing on the other side to compare them against.
Infrastructure service
Hosted remote access to Tenstorrent accelerator instances of 1-128 Wormhole Tensix processors, reached through a browser or remote session via the TT-Console portal.