M2 Max 64GB vs AMD RX 7900 XT for local LLMs
20 reports on the M2 Max 64GB and 10 on the AMD RX 7900 XT
Which is faster for local LLMs?
On Qwen2.5 7B at 4-bit, the M2 Max 64GB has 76.8 generation tokens/s (one run); prompt processing 602.8 tokens/s (one run); the AMD RX 7900 XT has 115.0 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 2.0x higher on the AMD RX 7900 XT (410 GB/s on the M2 Max 64GB, 800 on the AMD RX 7900 XT).
- Memory
- 64GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 20
- Memory
- 20GB
- Memory bandwidth
- 800 GB/s
- FP16 compute
- 103 TFLOPS
- Reports
- 10
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 | M2 Max 64GB | AMD RX 7900 XT |
|---|---|---|
| Qwen2.5 7B4-bit | 76.8one runPP 602.8 (one run)MLXcontext not stated | 115.0one runvLLMcontext not stated |
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 | M2 Max 64GB | AMD RX 7900 XT |
|---|---|---|
| Qwen2.5 7B | 20.1 t/sFP16 | 62.9 t/sQ8_0 |
| Qwen3.8 27B | 10.4 t/sQ8_0 | 37.2 t/sQ3_K_M |
| Qwen3.8 125B · 6B active | 47.5 t/sQ2_K | 19.2 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 32.9 t/sQ8_0 | 147.9 t/sQ3_K_S |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 10.4 t/sQ8_0 | 37.2 t/sQ3_K_M |
| Gemma 4 26B · 4B active | 28.2 t/sQ8_0 | 83.9 t/sQ4_K_S |
Change the context, RAM or model in the calculator: M2 Max 64GB · AMD RX 7900 XT
Every report on each card, with its source: M2 Max 64GB · AMD RX 7900 XT