M3 Max 128GB vs NVIDIA RTX 5090 for local LLMs
6 reports on the M3 Max 128GB and 169 on the NVIDIA RTX 5090
Which is faster for local LLMs?
On Qwen3.5 35B · 3B active at 4-bit, the M3 Max 128GB has 90.8 generation tokens/s (one run); the NVIDIA RTX 5090 has 194.0 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 4.4x higher on the NVIDIA RTX 5090 (410 GB/s on the M3 Max 128GB, 1,792 on the NVIDIA RTX 5090).
- Memory
- 128GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 14.2 TFLOPS
- Reports
- 6
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 169
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 | M3 Max 128GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.5 35B · 3B active4-bit | 90.8one runoMLXcontext not stated | 194.0one runllama.cppcontext 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 | M3 Max 128GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.5 35B · 3B active | 16.8 t/sFP16 | 163.0 t/sQ5_K_M |
| Qwen3.8 27B | 5.3 t/sFP16 | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | 24.3 t/sQ5_K_S | 20.3 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 16.8 t/sFP16 | 163.0 t/sQ5_K_M |
| DeepSeek V4 Flash 284B · 13B active | 38.2 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 5.3 t/sFP16 | 44.9 t/sQ6_K |
| Gemma 4 26B · 4B active | 14.4 t/sFP16 | 114.5 t/sQ6_K |
Change the context, RAM or model in the calculator: M3 Max 128GB · NVIDIA RTX 5090
Every report on each card, with its source: M3 Max 128GB · NVIDIA RTX 5090