Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
For compute-bound workloads like training, GH200 delivers 29.3× higher FP16 throughput.
Specifications
| GH200 | M4 Max (128 GB) | |
|---|---|---|
| VRAM | 96 GB | 96 GB |
| VRAM Type | HBM3 | LPDDR5X |
| Memory Bandwidth | 4.0 TB/s | 0.5 TB/s |
| FP16 Performance | 990 TFLOPS | 34 TFLOPS |
| Manufacturer | NVIDIA | Apple |
| FP8 Support | Yes | No |
| FP4 Support | No | No |
Price / Performance
Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.
| GH200 | M4 Max (128 GB) | |
|---|---|---|
| $/hr (cheapest) | $2.29 | — |
| $/TFLOP (compute value) | $0.0023 | — |
| $/GB VRAM (memory value) | $0.0239 | — |
Cloud Pricing
Cheapest on-demand price per provider (single GPU).
GH200
| Provider | On-demand | Spot | Rent |
|---|---|---|---|
| Lambda | $2.29/hr | — |
M4 Max (128 GB)
No cloud pricing available.
Model Compatibility
Models from the catalog that fit on each GPU, grouped by required precision.
GH200 (1000 models)
M4 Max (128 GB) (1000 models)
You might also compare…
Pricing data refreshed hourly · Last updated June 1, 2026 · Browse all comparisons