GPU Memory Math: Sizing VRAM for Full-Parameter Tuning
23d
- Published
- Collected
More from RunPod Blog
Log in to follow this source
Building Runpod templates part 2: Adding a Python API
Build a FastAPI and PyTorch service, package it with an explicit Docker startup command, and deploy it as an authenticated Runpod Pod template on a GPU.
Use Claude Code With Your Own Model on Runpod
If you've been using Claude Code with Anthropic's hosted models, you already know how powerful it is for AI-assisted development. But what if you could.
Qwen3.8-27B: Frontier-Class Coding on a Single 24GB GPU
Qwen 3.8 is punching well above its weight for its relatively small size compared to big foundational models. Is there a such thing as a free lunch?
AMD MI300X vs NVIDIA H100 SXM: Mixtral 8x7B Inference
Runpod benchmarks AMD's MI300X against Nvidia's H100 SXM using Mistral's Mixtral 8x7B model. The results highlight performance and cost trade-offs across.