Configuration
512131K
1128
VRAM Breakdown
Weights
7.00 GB
KV Cache
1.07 GB
Weight Overhead
0.70 GB
KV Overhead
0.02 GB
Total VRAM Required
8.80 GB
GPU Recommendations
| GPU | VRAM | GPUs | Utilization | Fit Check | Est. Price | Deploy |
|---|---|---|---|---|---|---|
🥇NVIDIA GB300 (Blackwell Ultra) | 288 GB | 1 | 3% | 🟢 Excellent | $8.00/hr | |
🥈AMD Instinct MI355X | 288 GB | 1 | 3% | 🟢 Excellent | $6.00/hr | |
🥉AMD Instinct MI350X | 288 GB | 1 | 3% | 🟢 Excellent | $5.50/hr | |
NVIDIA B300 (Blackwell Ultra) | 270 GB | 1 | 3% | 🟢 Excellent | $7.50/hr | |
AMD Instinct MI325X | 256 GB | 1 | 3% | 🟢 Excellent | $4.20/hr | |
Google TPU v7 Ironwood | 192 GB | 1 | 5% | 🟢 Excellent | $4.50/hr | |
NVIDIA B100 | 192 GB | 1 | 5% | 🟢 Excellent | $5.00/hr | |
AMD Instinct MI300X | 192 GB | 1 | 5% | 🟢 Excellent | $3.80/hr | |
AMD Radeon Instinct MI308X | 192 GB | 1 | 5% | 🟢 Excellent | $3.60/hr | |
NVIDIA GB200 | 186 GB | 1 | 5% | 🟢 Excellent | $6.50/hr | |
NVIDIA B200 | 180 GB | 1 | 5% | 🟢 Excellent | $5.50/hr | |
Amazon Trainium3 | 155 GB | 1 | 6% | 🟢 Excellent | $3.50/hr |