latent.fs / posts / ai / infra — 5 items

/feed.xml

CATEGORY

AI / Infra

2026-10 1 post

  1. Using Claude Subscription Credits for the API

    Which API paths the monthly credit covers on Max and Team plans, how to link an organization and manage keys, calls through the Python SDK, ant CLI, and Batch API, and how deduction and spend caps work

    AI·Infra #40

2026-07 1 post

  1. Driving a Free Colab GPU from the CLI

    google-colab-cli drives a free Colab GPU from your laptop. Worked example: serving PaddleOCR-VL on a T4 and running OCR on an invoice over a public URL.

    AI·Infra #33

2026-05 3 posts

  1. Apple Silicon LLM Inference — Five Backends Compared

    Qwen3.5-9B on MLX, llama.cpp, Ollama, omlx, and vLLM Metal. MLX led single requests at 25 tok/s; only omlx batched concurrent requests.

    AI·Infra #13

  2. NVIDIA NIM API — Free Inference for GLM, Kimi, Nemotron, and Gemma 4

    build.nvidia.com serves 100+ open models via a free OpenAI-compatible API, no credit card, up to 40 RPM per model. Setup for Claude Code and Cursor.

    AI·Infra #3

  3. GitHub Models Inference API — Free Model Access Tested

    Call GPT-4.1, DeepSeek R1, and other models free via GitHub Models with a personal access token and the OpenAI Python SDK. Rate and token limits apply.

    AI·Infra #5

TAGS 190

All 190 tags →