Skip to content
What are you looking for?. Open searchSR

Source

llama.cpp

3 items

The engine nearly every local runner is built on, release by release. Primary for which architecture it supports, which quantization formats exist, and what actually got faster.

github.com ↗

LLAMA.CPP0.4.0four architectures, one new transport
Machines & local modelsmedium signal

llama.cpp 0.4.0 adds four model architectures, an Apple RDMA transport, and video flags

The 0.4.0 release landed on September 4, 2026, and it is a numbered version rather than one of the nightly builds. It adds initial support for Qwen3.8-Flash-Next, NVIDIA Nemotron-3-Puzzle-75B-A9B, DSpark on Nemotron 3.5, and nanbeige4.2-3B. Apple RDMA becomes an RPC transport, video arrives as command-line options, and the quantizer gains a memory ceiling. Two server defaults changed, and saved session state carries a new version number.

llama.cppverified

LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
Machines & local modelsmedium signal

llama.cpp spent two days on long context, and the gains landed on three different backends

Between August 29 and 31, 2026, llama.cpp shipped a run of changes that all point at the same place: the part of inference that gets slower as the context grows. Vulkan, CUDA and the Metal and OpenCL paths each got their own fix, with numbers the authors published. Three crashes were closed alongside them. None of it needs a flag; it arrives with the next build.

llama.cppverified

Machines & local modelsstrong signal

Memory sets what you can run locally, and price per token sets whether you should

A local model has one hard requirement before speed, quality or license enter the discussion: the weights have to fit in memory. That turns the machine question into arithmetic you can do on paper, and Apple's August 25 desktops give you three price points to do it against — $899 for a 32GB ceiling, $2,499 for 128GB, $5,499 for 512GB. This guide works through what fits where, which runner to use, what each size class is good for, and how many tokens it takes before a machine beats paying by the token.

Apple, OpenRouter, DeepSeekverified