GPU Tools
Free, live-priced tools for sizing GPU workloads.
Training Cost Calculator
Estimate how long and how much it costs to pretrain a language model, priced against live GPU rates. Shows the full FLOPs formula.
GPU Recommender
Pick any popular Hugging Face model and get its VRAM requirement at native, FP8, and INT4 precision, plus the cheapest live GPU that fits.
Idle Cost Calculator
See what an idle GPU actually costs, priced against live per-GPU rates, and how much auto-pause saves you, since it works the same way on every provider.
VRAM Calculator
How much VRAM a model needs at FP16, FP8 or INT4, and which live GPUs actually fit it, or start from a card's VRAM and see what fits in it.
Popular models
Browse all models →google-bert/bert-base-uncased
0.1B params · F32
Qwen/Qwen3-0.6B
0.8B params · BF16
openai-community/gpt2
0.1B params · F32
Qwen/Qwen3-8B
8.2B params · BF16
Qwen/Qwen3.6-35B-A3B-FP8
36.0B params · F8_E4M3
Qwen/Qwen3.5-9B
9.7B params · BF16
Qwen/Qwen2.5-7B-Instruct
7.6B params · BF16
Qwen/Qwen3-VL-8B-Instruct
8.8B params · BF16
google/gemma-4-31B-it
31.3B params · BF16
google/gemma-4-26B-A4B-it
25.8B params · BF16
Qwen/Qwen3.6-27B-FP8
27.8B params · F8_E4M3
Qwen/Qwen2.5-VL-7B-Instruct
8.3B params · BF16
Qwen/Qwen2.5-1.5B-Instruct
1.5B params · BF16
Qwen/Qwen2.5-3B-Instruct
3.1B params · BF16
Qwen/Qwen3.5-4B
4.7B params · BF16
openai/whisper-large-v3-turbo
0.8B params · F16
Qwen/Qwen3-Embedding-0.6B
0.6B params · BF16
farbodtavakkoli/OTel-2.0-LLM-31B-IT
32.1B params · BF16
meta-llama/Llama-3.2-1B-Instruct
1.2B params · BF16
Qwen/Qwen3-4B
4.0B params · BF16
Qwen/Qwen2.5-0.5B-Instruct
0.5B params · BF16
meta-llama/Llama-3.1-8B-Instruct
8.0B params · BF16
Qwen/Qwen3.6-27B
27.8B params · BF16
MiniMaxAI/MiniMax-H3
33.1B params · BF16
