Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
M3 Ultra (192 GB) has 3 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, H200 SXM delivers 36.4× higher FP16 throughput.
Specifications
| H200 SXM | M3 Ultra (192 GB) | |
|---|---|---|
| VRAM | 141 GB | 144 GB |
| VRAM Type | HBM3e | LPDDR5 |
| Memory Bandwidth | 4.8 TB/s | 0.8 TB/s |
| FP16 Performance | 990 TFLOPS | 27 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.
| H200 SXM | M3 Ultra (192 GB) | |
|---|---|---|
| $/hr (cheapest) | $2.35 | — |
| $/TFLOP (compute value) | $0.0024 | — |
| $/GB VRAM (memory value) | $0.0167 | — |
Cloud Pricing
Cheapest on-demand price per provider (single GPU).
Model Compatibility
Models from the catalog that fit on each GPU, grouped by required precision.
H200 SXM (657 models)
M3 Ultra (192 GB) (657 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons