M2 Max 64GB vs M4 Max 48GB for local LLMs
4 reports on the M2 Max 64GB and 1 on the M4 Max 48GB
Which is faster for local LLMs?
On Qwen3.5 4B at 4-bit, the M2 Max 64GB runs at 70.4 tokens per second (one run) and the M4 Max 48GB at 85.0 (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 33% higher on the M4 Max 48GB (410 GB/s on the M2 Max 64GB, 546 on the M4 Max 48GB).
- Memory
- 64GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 4
- Memory
- 48GB unified
- Memory bandwidth
- 546 GB/s
- FP16 compute
- 18.4 TFLOPS
- Reports
- 1
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 | M2 Max 64GB | M4 Max 48GB |
|---|---|---|
| Qwen3.5 4B4-bit | 70.4one run | 85.0one 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 | M2 Max 64GB | M4 Max 48GB |
|---|---|---|
| Qwen3.5 4B | 35.2 t/sFP16 | 45.5 t/sFP16 |
| Qwen3.8 27B | 10.4 t/sQ8_0 | 16.6 t/sQ6_K |
| Qwen3.8 125B · 6B active | 47.5 t/sQ2_K | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 32.9 t/sQ8_0 | 66.0 t/sQ5_K_M |
| Qwen3.6 27B | 10.4 t/sQ8_0 | 16.6 t/sQ6_K |
| Gemma 4 26B · 4B active | 28.2 t/sQ8_0 | 32.3 t/sQ8_0 |
Change the context, RAM or model in the calculator: M2 Max 64GB · M4 Max 48GB
Every report on each card, with its source: M2 Max 64GB · M4 Max 48GB