#hardware
23 posts
2026 - October
7 postsLLM Benchmark: What Are the Best Open Source LLMs for Home Hardware?
I compared Basalt and Strata serving Qwen3.8 Flash-Next on an RTX 5090. Q2_0 scored 100 in all six hard runs and reached 400 tok/s on Basalt, versus 259 on Strata.
Best Open Source LLM: Strata with Qwen 3.8 Flash Next
Qwen3.8 Flash-Next served by the Strata engine scored 91, Tier A, on an RTX 5090, 1.5 points behind the B300 and at about 159 tokens per second. I explain how Strata fits a 125B MoE on a PC by using VRAM as an expert cache and RAM as the warehouse, why that matters with memory costing twice as much, and why it isn't magic: the 5090's memory bandwidth is seven times the Strix Halo's and almost 30 times PCIe's, and even on my machine it takes up almost all the RAM and VRAM. I show the install, a service that loads and unloads the model on its own, the OpenCode configuration, why I consider my machine the minimum for real programming work, and why, even a bit less responsive than a commercial model, it's already almost good enough to replace the cloud day to day.
LLM Benchmark v4: consumer-grade open source on RTX 5090 or Strix Halo. And Strata?
I went back to consumer hardware after the datacenter tests. Qwen3.8 Flash-Next scored 91.0, Tier A, on an RTX 5090 with the Strata engine, 1.5 points behind the B300 at 159 tokens per second. It's a different model from the Qwen 3.8 27B I had called slow: a MoE with 6B active per token, served with the hottest experts on the card. Strix Halo scored 80.0 with the 27B, but at 7.7 tokens per second. It's the first local model to make Tier A on the v4, and it's worth testing in day-to-day programming, if you can find a 5090: NVIDIA denies the end of production but admits tight supply.
LLM Benchmark v4: can my team fit in a 4x b300/h200?
After ranking the big models, the leftover question: how many developers fit on a 4x B300 or 4x H200 pod? We measured real concurrency, with a latency SLO, and the answer changes everything: DeepSeek V4.1 Flash holds 32 comfortable users on B300 and only 8 on H200. Cost per comfortable user: US$ 1.13/hour on B300 versus US$ 1.80 on H200. When your own infra closes the math against a frontier subscription, and when it's just expensive vanity.
LLM Benchmark v4: open source that only fits in 4x B300!!
I rented 4x NVIDIA B300 on Runpod and ran my v4 sabotage benchmark on the open models that don't fit on a single card. DeepSeek V4.1 Flash, at 748B, tied the leaders at 92.5, on the level of hosted GLM 5.3 and GPT-6 Sol. GLM 5.3 full fell behind, the 1T Kimi K2 Thinking disappointed, and a 397B model plummeted from 94 in the cloud to 27 at home. The math: US$ 36 per pod hour, US$ 864 per day. When owning your own infra makes sense, and whether a big open model is already enough for your day-to-day programming.
LLM Benchmark v4: the top open source LLMs on a B300
I rented a 288 GB NVIDIA B300 on Runpod and ran my v4 sabotage benchmark on 14 open-weight models that don't fit at home. None of them serves fast the way it ships: GLM 5.3 Flash went from 10 to 141 tokens per second on configuration alone. Two open models reached 92.5, Sonnet 5 level, and a 27B fine-tune scored 88. A 397B flagship let an admin backdoor through, DeepSeek V4 Flash scored 86 in the cloud and 44.5 at home, and Nemotron cheated on a test. The math: the cloud API of the same model costs a dollar per run and the pod costs 218 a day. When owning your own infra is worth it, and whether a team fits on one card.
Disaster on My NAS! How I Almost Lost 90 TB of Data
I swapped one drive in my Synology DS1821+ and woke up the next day with two critical drives in an array that only survives losing one. Full post-mortem: why SHR-1 wasn't enough, the warning DSM never sent, the R$ 185 thousand for a QNAP bought in a hurry, and the recovery: parallel NAS-to-NAS rsync, the slow drive holding the array back, the verification of 5.9 million files, the thick provisioning scare, and both NASes healthy in RAID-6.
2026 - August
2 postsIntel's Comeback: ARM64 vs X86-64 Is Not What You Think
Panther Lake already ties the Apple M5 in multi-core and delivers MacBook-class battery life in an x86 laptop. My thesis: the ISA hasn't defined efficiency since the 90s, and Intel's crisis was managerial, not architectural.
Exploiting Coinkite's RNG Egregious Problem
How an attacker enumerates the ColdCard's reduced key space, finds vulnerable wallets on the public blockchain, and moves the funds. Real data from the ongoing theft and step-by-step didactic code.
2026 - July
1 postURGENT - If You Keep Bitcoin on a ColdCard: MOVE EVERYTHING
An entropy flaw left seeds generated by ColdCard firmware far below the promised security level, with estimated losses above 1,000 BTC. Understand the bug and migrate without repeating the mistake.
2026 - April
2 postsOmarchy on the Thinkpad T14 Gen 6: Mini-Review and Full Setup
I installed Omarchy on a ThinkPad T14 Gen 6 and turned the laptop into a Linux companion for SSH, Claude Code, and NAS. The screen feels dated, but ports, durability, and support make up for it.
My Sim Racing Cockpit - Formula FX1
I replaced years of unstable stands with a Formula FX1 cockpit featuring Fanatec direct drive, PS5, RTX 4090, and a 4K OLED. It doesn’t wobble and is ready in 30 seconds for my single-player use.
2026 - March
1 postReview: Minisforum MS-S1 Max | AMD AI Max+ 395 with 96GB of VRAM
In my tests, the RTX 5090 was up to 7 times faster on models that fit within 32GB. The Minisforum, however, ran 50-to-81GB models the card can’t handle.
2026 - January
2 postsAI 3D: Can You Actually Model 3D With Prompts Now?
A practical walkthrough of generating high-quality 3D models from prompts and images using Nano Banana, Hunyuan, Hitem3D, and Blender, all the way to a physical Bambulab print.
Omarchy 3: Dual GPU Setup with AMD and NVIDIA
How I configured Hyprland on Omarchy to use an AMD iGPU as primary and offload 3D apps to an NVIDIA RTX 5090 via Prime.
2025 - May
1 postYour Windows May Be Crippled Without You Knowing. Check This!!
How a hidden Windows Power Saver profile was silently throttling a high-end desktop to a fraction of its real speed, and how to fix it.
2025 - April
2 postsNVIDIA and Wayland - Problems for PCI Passthrough in VMs
How GNOME on Wayland breaks live NVIDIA GPU passthrough to QEMU/Libvirt VMs, and the workaround scripts I use to make it work again.
BIOS Configuration of My PC - X670E Aorus Xtreme
My BIOS tuning notes for a Ryzen 9 7950X3D on a Gigabyte X670E Aorus Xtreme, plus Linux-Zen kernel and an automated BIOS update checker.
2017 - November
1 postFrom Microsoft to Apple, and Back Again
Comparing Windows 10, macOS, Linux, and premium laptops, the author concludes Windows deserves another chance, uses Manjaro in VirtualBox, and prefers a Dell XPS for development and a Surface Book 2 for design.
2017 - March
1 postEnabling Optimus NVIDIA GPU on the Dell XPS 15 with Linux, even on Battery
I fix a TLP and Bumblebee conflict on Manjaro running on a Dell XPS 15 by blacklisting the NVIDIA PCI device, restoring GPU use after suspend and while on battery.
2017 - January
2 postsFrom the Macbook Pro to the Dell XPS. Arch Linux for Creative Pro Users
I move from a MacBook Pro to a Dell XPS 9550 and configure Manjaro, Bumblebee, and NVIDIA drivers for creative tools. Linux works well, but Apple still has the edge for mobile Pro workflows.
Optimizing Linux for Slow Computers
I improve Linux responsiveness on an old Lenovo by tuning swap, schedulers, Dropbox, and Tracker. The biggest gains still come from adding more RAM and using a fast SSD.
2015 - November
1 postBrazil Situation: No Macs for the Rest of Us
I tested a Dell Inspiron with Ubuntu after a MacBook Pro became too expensive for a Brazilian budget. Linux covers about 80% of my use, but proprietary software still requires Mac or Windows.