M5 Max 36GB vs AMD RX 9070 XT 16GB for local LLMs
12 reports on the M5 Max 36GB and 18 on the AMD RX 9070 XT 16GB
Which is faster for local LLMs?
On Qwen3.5 9B at 4-bit, the M5 Max 36GB has 80.1 generation tokens/s (one run); the AMD RX 9070 XT 16GB has 7.9 generation tokens/s (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 39% higher on the AMD RX 9070 XT 16GB (461 GB/s on the M5 Max 36GB, 640 on the AMD RX 9070 XT 16GB).
- Memory
- 36GB unified
- Memory bandwidth
- 461 GB/s
- FP16 compute
- not on record
- Reports
- 12
- Memory
- 16GB
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 195 TFLOPS
- Reports
- 18
Measured on both
Generation and prompt processing speeds 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 bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | M5 Max 36GB | AMD RX 9070 XT 16GB |
|---|---|---|
| Qwen3.5 9B4-bit | 80.1one runengine not statedcontext not stated | 7.9one runllama.cpp32K context |
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 | M5 Max 36GB | AMD RX 9070 XT 16GB |
|---|---|---|
| Qwen3.5 9B | 20.3 t/sFP16 | 39.1 t/sQ8_0 |
| Qwen3.8 27B | 19.7 t/sQ5_K_M | 41.7 t/sQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 75.9 t/sQ4_K_M | 138.0 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 19.7 t/sQ5_K_M | 41.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 50.2 t/sQ5_K_M | 93.0 t/sQ3_K_S |
Change the context, RAM or model in the calculator: M5 Max 36GB · AMD RX 9070 XT 16GB
Every report on each card, with its source: M5 Max 36GB · AMD RX 9070 XT 16GB