AI and infrastructure news
Filter by type: Post13
Local LLM benchmarks on a Ryzen AI Max+ PRO 495 and the decision to return the machine
Throughput analysis of four large open-weight models run with llama.cpp/Vulkan on a 192 GB unified-memory APU, reporting 18 to 58 tps and a return made for cost reasons.
IPUs and small batches: cost versus ease of use
A post published on December 29, 2025 describes Graphcore IPUs as massively parallel accelerators suited to small batches, and says used units may cost little but can be difficult to use.
Exaviz board brings PoE and 2.5 Gbps uplink to compact NAS/NVR
Published on February 14, 2026, the report describes a Raspberry Pi Compute Module 5 board with eight PoE ports and a 2.5 Gbps uplink, designed for compact NAS or NVR builds.
Evaluating accelerators for parallel workloads
In a post published on September 18, 2025, Graphcore describes the IPU architecture and its resources for graph-based computing and irregular, sparse workloads.
High Bandwidth Flash: what to assess before 2026
In an article published on October 12, 2025, SanDisk proposes NAND-based memory with 8 to 16 times the capacity of HBM. First samples are expected in the second half of 2026.
Magnetic transistor could combine control and memory
An article dated September 23, 2025, reports that MIT researchers developed a transistor using a magnetic semiconductor, with potential to improve electrical control and integrate memory.
Triton: GPU data access with block pointers
Published on September 23, 2025, the post covers tensor storage and the use of tl.make_block_ptr, strides, and offsets in Triton kernels.
Crescent Island listed with 32 Xe3P cores and 480 GB LP5X
A publication dated August 24, 2026, lists Intel Crescent Island with 32 Xe3P cores, 480 GB of LP5X memory, and 350 W power consumption.
Dell Precision T7910: assessing a used multi-GPU platform
A publication dated July 17, 2026, lists the T7910 configuration and highlights PCIe slots, ECC memory, and power limits as factors in assessing multi-GPU computing.
ESP32 blocks 537,000 domains with about 50 KB of RAM
A post published on July 20, 2026 describes ESP32 firmware that stores its blocklist in flash and takes about 10 milliseconds to block requests.
Local AI: Mac Studio M5 Ultra or RTX PRO 6000?
A comparison of local AI configurations highlights differences in memory, CUDA support, prefill speed, cost, and noise.
Meta describes techniques to speed up storage
Published on July 5, 2026, Meta's post presents a storage architecture and performance techniques, including data locality, unified caches, and prefetching.
Xring O3: report cites 15,221 Geekbench 6 points
Published on August 24, 2026, the report attributes scores of 3,945 single-core and 15,221 multi-core to Xiaomi’s Xring O3, with the latter exceeding the Apple M4 result.
Let's assess your project
I reply with scope and a proposal.