M3 Max 128GB vs AMD Radeon AI PRO R9700 32GB for local LLMs
6 reports on the M3 Max 128GB and 43 on the AMD Radeon AI PRO R9700 32GB
Which is faster for local LLMs?
On Qwen3.5 35B · 3B active at 4-bit, the M3 Max 128GB runs at 90.8 tokens per second (one run) and the AMD Radeon AI PRO R9700 32GB at 149.2 (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 1.6x higher on the AMD Radeon AI PRO R9700 32GB (410 GB/s on the M3 Max 128GB, 640 on the AMD Radeon AI PRO R9700 32GB).
- Memory
- 128GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 14.2 TFLOPS
- Reports
- 6
- Memory
- 32GB
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 191 TFLOPS
- Reports
- 43
Measured on both
Median tokens per second from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same quant level. Engines and context lengths can still differ between the runs. How to read these
| Model | M3 Max 128GB | AMD Radeon AI PRO R9700 32GB |
|---|---|---|
| Qwen3.5 35B · 3B active4-bit | 90.8one run | 149.2one run |
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.
| Model | M3 Max 128GB | AMD Radeon AI PRO R9700 32GB |
|---|---|---|
| Qwen3.5 35B · 3B active | 16.8 t/sFP16 | 58.2 t/sQ5_K_M |
| Qwen3.8 27B | 5.3 t/sFP16 | 16.0 t/sQ6_K |
| Qwen3.8 125B · 6B active | 24.3 t/sQ5_K_S | 18.7 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 38.2 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 16.8 t/sFP16 | 58.2 t/sQ5_K_M |
| Qwen3.6 27B | 5.3 t/sFP16 | 16.0 t/sQ6_K |
| Gemma 4 26B · 4B active | 14.4 t/sFP16 | 40.9 t/sQ6_K |
Change the context, RAM or model in the calculator: M3 Max 128GB · AMD Radeon AI PRO R9700 32GB
Every report on each card, with its source: M3 Max 128GB · AMD Radeon AI PRO R9700 32GB