RemyBlog
By role

AI for Engineering

How engineers use AI, how to do it well, and what it means for your job. Written for people who ship and run the software, not people who build models.

458 articles · Updated Nov 13, 2026
Tiny figurines inspect the printed itemized lines of a giant receipt.
AI Pricing & Costs ·

How Do You Access Inkling 2 Small and What Does It Cost?

Inkling 2 Small is available only through the Thinking Machines console with paid API credits. Here is what access looks like and what the $426 run shows.

Inkling 2 Small pricingThinking Machines APIInkling 2 console access
Tiny figurines are plugging network cables into the different blades of a giant server rack.
AI Coding Tools ·

What's New in Herdr 0.9.5 for Running Coding Agents?

Herdr 0.9.5 adds multi-machine SSH, the --machine flag, per-client UI, safer updates, session persistence and agent self-reporting. Here is what to know.

HerdrHerdr 0.9.5terminal multiplexer coding agents
A minimalist 3D illustration of an Olares One mini server box interacting with a floating, semi-transparent terminal window filled with glowing code.
Local AI ·

How Do You Control an Olares One With a Coding Agent?

How a coding agent like Codex or Claude Code can drive an Olares One: what the setup involves, example prompts for STL files and ComfyUI, and what to verify.

Olares OneOlares CLIcoding agent
A person holds a giant review form up to the light, using a magnifying glass to inspect tiny lines of HTML code, vision charts, and circuit diagrams printed on the paper.
AI Models & Industry ·

Inkling 2 Small Review: How Good Is Thinking Machines' MoE?

Inkling 2 Small is a 594B-parameter, 17B-active multimodal MoE. Hands-on tests in HTML, multilingual output, circuits and vision, plus benchmark standing.

Inkling 2 SmallThinking Machines InklingInkling 2 review
Tiny figurines shave down a large data block to fit onto the memory chips of a giant RAM stick.
Local AI ·

Can You Run Local AI on a Weak Linux Machine With Low RAM?

Run local AI on a weak Linux machine with 4GB RAM and no GPU: the RAM budget, model sizes that fit, Ollama setup, and realistic CPU-only speeds.

local ai on weak linux machinerun local llm on low memory linuxsmall llm for 4gb ram cpu only
A 3D rendering of a semi-transparent command line terminal window physically etched into a thick, glowing block of silicon computer hardware.
Local AI ·

How to Run StarCoder2 15B Locally: Hardware and Commands

Run StarCoder2 15B locally with Ollama or llama.cpp. Install commands, approximate quantized sizes, and the VRAM or unified memory each setup needs.

run starcoder2 15b locallystarcoder2 15b ollamastarcoder2 15b vram requirements
A terminal window made of thick, frosted acrylic stands upright on a desk, displaying brightly glowing server installation commands.
Local AI ·

How Do You Run DSpine With Qwen3.8-27B on SGLang?

Set up Tencent's DSpine draft model with Qwen3.8-27B on SGLang: install steps, serve flags, block size 16, H100 memory use and the A100 problem.

run DSpine SGLangQwen3.8-27B SGLangDSpine install
A 3D rendering of a benchmark bar chart interface where one data bar stretches impossibly high, breaking past the top edge of the panel.
Local AI ·

DSpine vs DFlash2: How Much Faster Is It? Benchmarks

DSpine vs DFlash2 on Qwen3.8-27B: acceptance length, agent throughput, and a hands-on H100 test that hit about 156 tokens/s versus 33.

DSpine vs DFlash2DSpine benchmarksacceptance length
A person slides a paper voting ballot into a narrow slot on a massive AI server rack, causing the machine's glowing lights to power down.
AI Models & Industry ·

How Will Data Center Ballot Defeats Affect AI Compute?

Local votes blocked data centers while AI use climbs. Here is how that hits neo clouds, big tech, offshore siting, overbuild risk and orbital compute.

data center vote AIAI data center backlashneo cloud risk
A person holds a long filmstrip printed on thermal receipt paper up to the light, examining the itemized cost per second of video.
AI Pricing & Costs ·

How Much Does Gemini Omni 1.2 Flash Cost Per Clip?

Gemini Omni 1.2 Flash costs about 7 cents per second at 720p. See what a 3 to 15 second clip costs and how draft-then-upscale to 1080p or 4K works.

Gemini Omni 1.2 Flash pricingGemini video generation costOmni 1.2 Flash 15 seconds
A person uses digital calipers to measure a giant laptop, a standard laptop, and a tiny microscopic laptop lined up side-by-side on a desk.
Local AI ·

Northka Computer Use Model: Which Size and How Good?

Northka is an open-weight computer-use model family (397B Pro, 35B Mini, 9B Nano) scoring 78.9 to 88 on OSWorld Verified. Sizes, scores and harness explained.

Northka computer use modelNorthka OSWorldopen source computer use agent