AI Weekly Malaysia

Summaries

Short AI and tech summaries with source links, signal scores, and why each update matters for builders, founders, and Malaysian tech workers.

Reset

Showing 1-4 of 4 results

DateProviderScoreSummary
18 Nov 2026, 8:00 AMHugging Face Blog7.8 180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers

Tarek Ziadé's Hugging Face post experiments with running a 180B-parameter MoE model on a 32GB Mac by streaming experts from SSD, reporting that this approach gets within 6% of Strata on token generation. The post covers the author's setup—two RTX 4090s on Windows 11 plus an M5 MacBook with 32GB unified memory—and prior tests running Qwen 3.8 27B via llama.app and Qwen3.8-Flash-Next via Strata. It notes a 32GB M4 result of 13.5 tok/s, too slow for coding agents, and frames expert offload as a way to run MoE models that do not fit in unified memory.

Why: If you run local coding agents, use the reported numbers as a decision threshold: a 180B MoE can fit with SSD expert streaming, but 13.5 tok/s on a 32GB M4 is not interactive for agent loops, so benchmark your own model and engine before treating extra VRAM as the only fix. The 6% gap to Strata also makes offload engines worth testing before upgrading a 32GB Mac.

19 Nov 2026, 5:00 AMTom's Hardware4.5 Nvidia GeForce driver bug reportedly hammers SSDs with up to 30GB of writes per hour

Tom's Hardware reports that users have traced heavy idle SSD wear — up to 30GB of writes per hour — to an Nvidia GeForce driver background service, and that a newer driver is reportedly still affected. The available text is only the headline and page boilerplate: it names no specific driver versions, no Nvidia response, and no confirmed fix or workaround.

Why: If you run a GeForce card in a dev workstation or a local-LLM rig that idles 24/7, 30GB/hour of background writes is a real endurance cost on consumer SSDs — but with no version numbers in this report you can't tell whether you're affected. Measure before acting: check your drive's Total Host Writes / SMART data over a day, then again a day later, instead of switching drivers on an unconfirmed report.

17 Nov 2026, 9:13 PMTom's Hardware2.5 Phison Pascari X201P 15.36TB SSD Review: Fast PCIe 5.0 write performance for AI and ingest servers

Tom's Hardware published a review of the Phison Pascari X201P, a 15.36TB PCIe 5.0 SSD positioned for AI and ingest servers. The supplied text contains only the headline and page boilerplate, so it provides no benchmark results, pricing, endurance ratings, or comparison data.

Why: If you are choosing storage for AI or ingest servers, the only concrete takeaway is that a 15.36TB PCIe 5.0 drive is being reviewed for that niche; there is not enough detail here to justify shortlisting it or changing a procurement decision until sustained-write benchmarks, endurance, and price are available.

17 Nov 2026, 8:32 PMTom's Hardware1.0 How we test enterprise SSDs

The item is titled 'How we test enterprise SSDs' and claims a new test suite pushes enterprise and data-center SSDs to their limits, but the supplied text is almost entirely Tom's Hardware membership, newsletter, and premium-access boilerplate. No actual test methodology, benchmark numbers, SSD models, thresholds, or results are included in the excerpt.

Why: There is no concrete takeaway for builders here: the excerpt gives no methodology, measurements, or model comparisons, so it cannot inform an enterprise SSD purchase, database deployment, or storage benchmarking decision. Readers would need the full article or independent benchmark data before acting on the title's claim.

Top