User pretrained a 500M parameter LLM and a 330M image generator from scratch on 8xH200 from modal.com. The total cost was $800, and GGUF weights are included. User mentions pretraining a 1B model next.
HobbyLM
1 report
HobbyLM VRAM requirements by size and quant →How does HobbyLM run on your hardware?
Pick your GPU or Mac, then read the speeds people reported for HobbyLM on it, or estimate memory fit and speed.
Free to use. No account needed. Memory estimates and community measurements are labelled separately.
Run HobbyLM yourself? Add your numbers.
Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.
Reported performance for HobbyLM
Filter this model’s reports by setup →Thin page (1 of 3 reports needed for indexing). Add yours.
Get a weekly email of new HobbyLM reports on any GPU.
Email me new reports