Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
M4 (24 GB) has 2 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, RX 9070 XT delivers 23.2× higher FP16 throughput.
Specifications
| M4 (24 GB) | RX 9070 XT | |
|---|---|---|
| VRAM | 18 GB | 16 GB |
| VRAM Type | LPDDR5X | GDDR6 |
| Memory Bandwidth | 0.1 TB/s | 0.6 TB/s |
| FP16 Performance | 8 TFLOPS | 195 TFLOPS |
| Manufacturer | Apple | AMD |
| FP8 Support | No | Yes |
| FP4 Support | No | No |
Price / Performance
Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.
| M4 (24 GB) | RX 9070 XT | |
|---|---|---|
| $/hr (cheapest) | — | — |
| $/TFLOP (compute value) | — | — |
| $/GB VRAM (memory value) | — | — |
Cloud Pricing
Cheapest on-demand price per provider (single GPU).
M4 (24 GB)
No cloud pricing available.
RX 9070 XT
No cloud pricing available.
Model Compatibility
Models from the catalog that fit on each GPU, grouped by required precision.
M4 (24 GB) (1000 models)
RX 9070 XT (1000 models)
You might also compare…
Pricing data refreshed hourly · Last updated June 1, 2026 · Browse all comparisons