Fractile is one of several inference-focused startups pursuing SRAM-based or near-memory architectures, including Groq and Cerebras. Nvidia struck a $20 billion acquisition deal with Groq in December and subsequently launched its own dedicated inference accelerator, Groq 3 LPX , acknowledging the growing commercial pressure to optimize cost-per-token at scale.
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Luke James is a freelance writer and journalist.\u00a0 Although his background is in legal, he has a personal interest in all things tech, especially hardware and microelectronics, and anything regulatory.\u00a0 ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-22/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Luke James Social Links Navigation Contributor Luke James is a freelance writer and journalist. Although his background is in legal, he has a personal interest in all things tech, especially hardware and microelectronics, and anything regulatory.
alan.campbell99 2027, assuming Anthropic doesn't fall over and die if the bubble pops. How will they pay for these on top of all their other commitments alongside their insane cash burn. This ARR that gets thrown around is a have, I believe to date they've made something like 5 billion? They have this apparent surging demand yet still signing up as many customers as they can get their hands on? At least there as a token acknowledgement of their inference costs, neither they nor openAI are profitable here. I do wish some tech reporters would stop blindly accepting details from known liars and con men, maybe start being a bit more critical instead of carrying these guy's water. Reply
American2021 alan.campbell99 said: 2027, assuming Anthropic doesn't fall over and die if the bubble pops. How will they pay for these on top of all their other commitments alongside their insane cash burn. This ARR that gets thrown around is a have, I believe to date they've made something like 5 billion? They have this apparent surging demand yet still signing up as many customers as they can get their hands on? At least there as a token acknowledgement of their inference costs, neither they nor openAI are profitable here. I do wish some tech reporters would stop blindly accepting details from known liars and con men, maybe start being a bit more critical instead of carrying these guy's water. It is a private LLC so no financials available at the sec.gov website. Their detailed internal financials remain confidential and unavailable. This fuels a lot of speculation and interesting reporting. That said they did file a Form D which can be accessed in the EDGAR database but there is very limited data there. Presently, there is a lot of speculative reporting around Anthropic PBC with the usual suspects (e.g., Crunchbase, PitchBook, Bloomberg, etc.) that report on private company valuations likely off track to whatever degree they are. Reply
bit_user The article said: Fractile is one of several inference-focused startups pursuing SRAM-based or near-memory architectures, including Groq and Cerebras. Yes, most purpose-built AI chips I've read about seem to do this, including Tenstorrent and Graphcore (defunct, I think). The downside is that it takes potentially lots and lots of chips, in order to use it for inferencing large models. Reply
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/anthropic-in-early-talks-to-buy-inference-chips-from-uk-startup-fractile#main
- https://www.tomshardware.com
- Microsoft now recommends 32GB of RAM as the future-proof 'no worries' config for gaming — 16GB becomes the new 'practical starting point' during the RAMageddon
- Intel's Arc Pro B70 workstation GPU with 32GB of VRAM gets tested in games — Roughly twice as fast as Arc B580 on average, beats RTX 5060 Ti in some titles
- Secretlab launches Mandalorian Titan Evo gaming chair in Star Wars collection for May the 4th — collab builds with a new high-end themed chair
- New server-focused SPEC CPU 2026 benchmarking suite has results for a Raspberry Pi 5 — updated tools feature more tests and can run a wide range of systems
- Retailer selling broken RTX 5090 GPUs for as low as $1,760 — GPUs were damaged during transport, but include all components on the PCB
Informational only. No financial advice. Do your own research.