M2 Max 96GB vs NVIDIA RTX 5090 for local LLMs
7 reports on the M2 Max 96GB and 169 on the NVIDIA RTX 5090
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 4.4x higher on the NVIDIA RTX 5090 (410 GB/s on the M2 Max 96GB, 1,792 on the NVIDIA RTX 5090). The estimates below compare them on the models people run most.
M2 Max 96GB
- Memory
- 96GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 7
NVIDIA RTX 5090
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 169
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.
| Model | M2 Max 96GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.8 27B | 5.2 t/sFP16 | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | 36.2 t/sQ3_K_M | 20.3 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 37.6 t/sQ8_0 | 163.0 t/sQ5_K_M |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 5.2 t/sFP16 | 44.9 t/sQ6_K |
| Gemma 4 26B · 4B active | 12.5 t/sFP16 | 114.5 t/sQ6_K |
Change the context, RAM or model in the calculator: M2 Max 96GB · NVIDIA RTX 5090
Every report on each card, with its source: M2 Max 96GB · NVIDIA RTX 5090