@steeve: 4x Intel Optane P5800X hellyeah.jpg
Summary
A tweet showcasing four Intel Optane P5800X storage devices, accompanied by an image and a link for more details.
View Cached Full Text
Cached at: 08/19/26, 06:47 AM
4x Intel Optane P5800X
hellyeah.jpg https://t.co/Z1SRg1UskV
Similar Articles
intel optane for AI workloads
Intel's discontinued Optane persistent memory technology is finding a second life in AI workloads, enabling a user to run a 1 trillion parameter model locally at ~4 tokens/second using cheap second-hand Optane modules. The article highlights Optane's lower latency compared to SSDs, making it suitable for large model inference despite being slower than DRAM.
Computer build using Intel Optane Persistent Memory - Can run 1 trillion parameter model at over 4 tokens/sec
A community member details a custom PC build using discontinued Intel Optane Persistent Memory to successfully run the 1-trillion parameter Kimi K2.5 model locally at roughly 4 tokens per second via llama.cpp.
Kioxia and Dell cram 10 PB into slim 2RU server
Kioxia and Dell have collaborated to create a 2RU server with nearly 10 PB of all-flash storage using 40 Kioxia LC9 245.76 TB SSDs, enabling high-density AI infrastructure.
@Prince_Canuma: My home compute for MLX and research: • M3 Ultra — 512GB (sponsored by community + @wai_protocol) • RTX PRO 6000 — 96GB…
A researcher shares their home compute setup for MLX and AI research, featuring M3 Ultra with 512GB, RTX PRO 6000 with 96GB, and M3 Max with 96GB for model porting and stress testing.
Intel's Crescent Island PCB Leaks, Showing a Massive Xe3P GPU, 16-Pin Connector, 160GB LPDDR5X as Intel Sidesteps the HBM Shortage
Leaked PCB images reveal Intel's upcoming Crescent Island AI accelerator, featuring a large Xe3P GPU and 160 GB of LPDDR5X memory, designed as a cost-effective alternative to HBM-based solutions for AI inference.