GPU Advisor
Two questions, two modes. Pick a GPU you own — see what runs on it. Or pick the models you want — see which GPUs are big enough.
Every one of the 97 models in the catalogue gets an answer for every one of the 27 cards — 2619 verdicts, drawn from 950 published recipes. A model is never silently left out of the list because we cannot prove it runs; it is labelled untested and stays in.
loading advisor…
Four answers, and why they are not symmetric
- verified
- a published recipe targets this exact model and this exact card.
- fits
- no recipe for the pair, but one on the same vendor's hardware puts the memory floor at or below this card.
- won't fit
- a floor measured on any platform is above this card's memory.
- untested
- it fits in memory as far as we know, and nothing establishes a runtime path.
The evidence rule is deliberately lopsided, because the two claims it has to make are not the same kind of claim. Ruling a card out is arithmetic on bytes. If a recipe anywhere — CUDA, ROCm, Metal — recorded that a model needed more memory than your card has, that number rules the card out, because memory is memory whoever measured it.
Ruling a card in is a claim about software. It says a runtime exists, builds, and loads that architecture on your platform — and that does not travel. A model with a comfortable CUDA recipe may have no working Metal path at all. So fitsis only ever inferred from a recipe on the same vendor's hardware, and a model that clears the memory bar with no same-vendor evidence is reported as untested rather than promoted.
The one exception is VRAM-budget mode, where you type a number instead of naming a card. There is no platform to scope to and no runtime claim to over-reach on, so the memory floor answers in both directions.
27 GPUs, and how much evidence backs each
Recipe count is the number that matters here. Benchmarks are ingested opportunistically and are far sparser; recipes are the written, reproduced setups the verdicts above are derived from. A card near the bottom of this column will show more untested rows — that is a gap in our coverage, not a verdict about the hardware.
| GPU | Vendor | Memory | Recipes | Benchmarks |
|---|---|---|---|---|
| RTX 3060 | nvidia | 12 GB | 36 | 11 |
| RTX 3060 Ti | nvidia | 8 GB | 26 | 11 |
| RTX 3080 Ti | nvidia | 12 GB | 35 | 4 |
| RTX 3090 | nvidia | 24 GB | 45 | 21 |
| RTX 3090 Ti | nvidia | 24 GB | 38 | 12 |
| RTX 4060 | nvidia | 8 GB | 14 | 0 |
| RTX 4060 Ti 8GB | nvidia | 8 GB | 12 | 0 |
| RTX 4060 Ti 16GB | nvidia | 16 GB | 36 | 7 |
| RTX 4070 | nvidia | 12 GB | 42 | 1 |
| RTX 4070 Super | nvidia | 12 GB | 36 | 4 |
| RTX 4070 Ti | nvidia | 12 GB | 35 | 6 |
| RTX 4070 Ti Super | nvidia | 16 GB | 43 | 6 |
| RTX 4080 | nvidia | 16 GB | 49 | 6 |
| RTX 4080 Super | nvidia | 16 GB | 43 | 5 |
| RTX 4090 | nvidia | 24 GB | 47 | 6 |
| RTX 5060 | nvidia | 8 GB | 14 | 3 |
| RTX 5060 Ti | nvidia | 16 GB | 44 | 8 |
| RTX 5070 | nvidia | 12 GB | 35 | 4 |
| RTX 5070 Ti | nvidia | 16 GB | 43 | 7 |
| RTX 5080 | nvidia | 16 GB | 43 | 7 |
| RTX 5090 | nvidia | 32 GB | 48 | 26 |
| RX 7800 XT | amd | 16 GB | 45 | 0 |
| RX 7900 XTX | amd | 24 GB | 49 | 3 |
| Apple M2 Max | apple | 64 GB | 27 | 0 |
| Apple M2 Pro | apple | 16 GB | 17 | 0 |
| Apple M3 Max | apple | 48 GB | 27 | 0 |
| Apple M4 Max | apple | 48 GB | 19 | 0 |
Common questions
Where do the verdicts come from?
Published recipes, not benchmark ingestion. A recipe is a setup someone wrote down and ran, and it records the peak VRAM the run actually needed. Those figures become the memory floors every other verdict is measured against, which is why a card with many recipes answers more confidently than one with few.
Why does it say a model fits when nobody has run it on my card?
Because the two directions are not equally safe to guess. "It will not fit" is a statement about bytes, and bytes do not care which platform measured them, so a floor recorded anywhere can rule a card out. "It fits" is a statement about a working runtime, which does not transfer between CUDA, ROCm and Metal — so it is only inferred from a recipe on the same vendor's hardware. Anything that satisfies neither test is reported as untested rather than guessed.
Does it account for context length?
Only as far as the recipe it learned the floor from did. Every floor comes from a real run at whatever context that recipe used, and the recipe says which. Doubling the context raises the KV-cache cost and can push a model that fits at 8k over the edge at 128k, so treat a bare "fits" as a claim about a default-ish context and read the recipe for the number.
Why can I open a recipe from some rows and not others?
A row links onward only when the verdict is verified, because that is the only tier where a document exists for that exact pair. Linking every row would point at pages that were never generated — compatibility pages exist for covered pairs, not for all 97 models times 27 cards.
The advisor and the comparison table disagree with a GPU page. Which is right?
None of them should disagree: the advisor, the side-by-side comparison and each GPU page all read the same recipe evidence through the same code path, and a test walks a comparison row by row against the advisor's answer for each card to keep it that way. If you do find a contradiction it is a bug worth reporting, not a difference of opinion.
Comparing specific cards instead? Put two to four side by side.