Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: llama-cpp
TensorFold vs llama.cpp on a Mac Studio M5 Ultra: 1.84x the Throughput on Real JSON Work
I benchmarked TensorFold 1.2.0 against llama.cpp on a Mac Studio M5 Ultra with Qwen3.8-27B and 80 real JSON requests: 1.84x throughput at 8 concurrent.
9 min readHy-MT2-7B on Five Local Runtimes: Which One Should Serve Translation on a Mac?
Hy-MT2-7B load-tested on llama.cpp, LM Studio, mlx-lm, Ollama and MLX-Serve on two Mac Studio M5 Ultra machines: throughput, scaling, determinism, memory.
9 min readDeepSeek Harness (dsh): The Open Agent Runtime That Rewrites Its Own Config
What DeepSeek Harness is, why its self-editing agent stands out, how the community reacted, and what to prepare for before running it with local models.
6 min readRunning Kimi K3 and Other Big Models Locally with Five Open Repos
Five open source repos that squeeze frontier-scale models onto a laptop or single GPU, using disk streaming, expert caching and offloading, with their real speed numbers.
6 min readRun a Local Coding Model With llama.cpp: Quantization, Context Window and VS Code
Swap metered token bills for a local MoE model: pick a quantization, size the context window, tune llama-server for small CUDA GPUs, then connect Cline.
8 min readLocal LLM Workstation: From 20 to 60 Tokens per Second with Two GPUs
A used Xeon box with two RTX 5060 Ti cards, Qwen 27B, tensor parallelism and NCCL: hardware rules, real speed gains, and a break-even calculation against API pricing.
9 min readWhy Ollama Stops Being Enough and What to Run Instead
Ollama is a wrapper around llama.cpp. Learn where it hits limits on load, model formats and AMD GPUs, and when llama.cpp, LM Studio or vLLM fits better.
7 min readDoubling Qwen3.8-Flash-Next Decode Speed with MTP on RTX GPUs
Learn how to build a llama.cpp fork with MTP speculative decoding and the right flags to roughly double Qwen3.8-Flash-Next generation speed on multi-GPU RTX rigs.
5 min readQwen3.8-Flash-Next: A 177B Model That Runs on One 24GB GPU
How Qwen3.8-Flash-Next fits a 177B mixture-of-experts model onto modest hardware with 6B active parameters, an n-gram table and hybrid attention, plus its benchmark gaps.
9 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.