Free playground · no account

Will it fit on your GPU?

Everyone asks it before downloading an open model — almost nobody shows the arithmetic. Pick a size, a quantization and a context length, and read the VRAM bill line by line.

Weights — 70B params × 0.5 bytes33 GB
KV cache — 2 × 80 layers × 1024 kv-dim × 2 B × 8,192 tokens2.5 GB
Runtime overhead (~10%)3.5 GB
Estimated VRAM needed39 GB
RTX 3060 (12 GB) won't fit
RTX 4070 Ti (12 GB) won't fit
RTX 4090 (24 GB) won't fit
Mac 32GB unified (24 GB) won't fit
Mac 64GB unified (48 GB) fits
A100 40GB (40 GB) fits
A100 80GB (80 GB) fits
H100 80GB (80 GB) fits
Cheapest fit: Mac 64GB unifiedPlanning estimates for representative open-weights architectures — measure before you buy.
The Demystify reveal

The VRAM math is shown line by line — weights, KV cache at your exact context length, and runtime overhead — not a yes/no verdict from a black box. Change one dial and watch which line moves.

Why does context length change the memory a model needs?

Every token in the context keeps its key/value tensors cached on the GPU for attention. Double the context and the KV cache roughly doubles — at long contexts it can rival the weights themselves.

What does 4-bit quantization actually do?

It stores each weight in 4 bits instead of 16, cutting weight memory to a quarter at a small quality cost. It's the single biggest lever for fitting large models on consumer GPUs.

Are these numbers exact for a specific model?

No — they're honest planning estimates for representative open-weights architectures at each size class. Real usage varies with the runtime, attention implementation and batch size; measure before you buy hardware.

This playable is part of the registry: its tool page

Next: see what your words cost

The Tokenizer Lab shows the tokens a model actually reads — the unit every context window and API bill is counted in.