Apple M1 Pro (32 GB unified memory) vs. AMD Radeon RX 9070 (16 GB dedicated VRAM)
Both systems ran the identical standard-ai-v0.1 methodology: the same byte-identical model files (verified by SHA-256), the same llama.cpp build, the same context depth and repetition count. That is what makes this comparison meaningful — see Methodology.
8b-q4
Prompt processing (tok/s)
AMD Radeon RX 9070 (16 GB dedicated VRAM) measured 13.19× the prompt-processing throughput of Apple M1 Pro (32 GB unified memory) in this specific workload.
Generation (tok/s)
AMD Radeon RX 9070 (16 GB dedicated VRAM) measured 3.67× the generation throughput of Apple M1 Pro (32 GB unified memory) in this specific workload.
14b-q4
Prompt processing (tok/s)
AMD Radeon RX 9070 (16 GB dedicated VRAM) measured 12.13× the prompt-processing throughput of Apple M1 Pro (32 GB unified memory) in this specific workload.
Generation (tok/s)
AMD Radeon RX 9070 (16 GB dedicated VRAM) measured 4.81× the generation throughput of Apple M1 Pro (32 GB unified memory) in this specific workload.
| Apple M1 Pro (32 GB unified memory) | AMD Radeon RX 9070 (16 GB dedicated VRAM) | |
|---|---|---|
| Memory architecture | unified-memory | dedicated-vram (see hardware page for provenance) |
| Backend | BLAS,MTL | Vulkan |
| Methodology | standard-ai-v0.1 | standard-ai-v0.1 |
| Accelerator verification | 33/33, 41/41 layers offloaded to GPU | 33/33, 41/41 layers offloaded to GPU |
| Telemetry (power/temp) | UNAVAILABLE | UNAVAILABLE |
This is not a single score. RigRoute Labs does not name an overall winner — the numbers above describe two specific, measured dimensions of one specific workload, nothing broader.