Tool · Run a model
Will my model fit on this GPU?
Compute the VRAM you need for a given AI model at a chosen precision and context window, and see exactly which rentable GPUs have the headroom — plus the cheapest provider for each.
Active params
70.0B
Dense
Bytes / param
2.0
FP16
Context
128,000
tokens
VRAM required
179 GB
weights + KV + 20% headroom
GPUs that fit
Sorted by VRAM ascending — smallest fitting card first (usually the cheapest).
| GPU | VRAM | FP16 TFLOPS | TDP | Cheapest provider | $/hr | |
|---|---|---|---|---|---|---|
| 192GB | — | 1000W | DeepInfra | $2.79/hr | Open → | |
| 192GB | — | — | TensorWave | $1.95/hr | Open → | |
| 192GB | — | 750W | no live offers | — | Open → | |
| 192GB | — | — | no live offers | — | Open → | |
| 256GB | — | 1000W | no live offers | — | Open → | |
| 288GB | — | 1400W | no live offers | — | Open → | |
| 288GB | — | 1400W | io.net | $5.38/hr | Open → | |
| 288GB | — | — | no live offers | — | Open → | |
| 288GB | — | 2700W | no live offers | — | Open → |
