BTC
ETH
USDT
XMR
LTC
AI models & sizing10 min read
Self-host an LLM: a private ChatGPT on your own GPU server
How to self-host an LLM as a private ChatGPT: pick an open model, size the GPU, run Ollama with Open WebUI or vLLM, lock down access, and what it costs.
Blog · GPU
Articles about AMD MI355X.
5 articles cover the AMD MI355X. Rent it from $1,409 per GPU per month, paid in crypto: AMD MI355X servers.
14 articles5 topicsUpdated RSS feed
AMD MI355X
5 articles · newest first
AI models & sizing10 min read
Best GPU for LLM inference in 2026: memory, bandwidth and price
Best GPU for LLM inference in 2026: VRAM, bandwidth and price of 10 GPUs, and the cheapest server for each model size, from 8B to 1T.
AI models & sizing5 min read
How much GPU memory (VRAM) does your model need?
Formulas for weights, KV cache and training memory, worked examples for Llama 3.1, Qwen3, gpt-oss and DeepSeek, and the GPU servers that fit each model.
GPU hardware5 min read
B300 vs B200 vs H200 vs MI355X: which flagship GPU to rent
Verified specs of the B300, B200, H200 and MI355X: memory, bandwidth, links, FP8, FP4 and FP64, with price per GB of GPU memory and the workloads each suits.
GPU hardware4 min read
AMD MI355X: 288 GB of HBM3E at an H100-class price
The AMD MI355X pairs 288 GB of HBM3E and 8 TB/s with a price below the H100: specs, ROCm support, caveats and memory per dollar vs the H100 and H200.
From reading to running.
Every GPU in these articles is available by the month, about 30% under the market median.