M4 Max 128GB vs NVIDIA RTX 5090 for local LLMs
17 reports on the M4 Max 128GB and 126 on the NVIDIA RTX 5090
Which is faster for local LLMs?
On Qwen3 30B · 3B active at 4-bit, the M4 Max 128GB runs at 127.7 tokens per second (one run) and the NVIDIA RTX 5090 at 352.1 (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 3.3x higher on the NVIDIA RTX 5090 (546 GB/s on the M4 Max 128GB, 1,792 on the NVIDIA RTX 5090).
- Memory
- 128GB unified
- Memory bandwidth
- 546 GB/s
- FP16 compute
- 18.4 TFLOPS
- Reports
- 17
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 126
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 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 | M4 Max 128GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3 30B · 3B active4-bit | 127.7one runvllm-mlxcontext not stated | 352.1one 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 | M4 Max 128GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3 30B · 3B active | 23.7 t/sFP16 | 262.8 t/sQ4_K_S |
| Qwen3.8 27B | 6.7 t/sFP16 | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | 30.7 t/sQ5_K_S | 20.3 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 48.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 21.2 t/sFP16 | 163.0 t/sQ5_K_M |
| Qwen3.6 27B | 6.7 t/sFP16 | 44.9 t/sQ6_K |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M4 Max 128GB · NVIDIA RTX 5090
Every report on each card, with its source: M4 Max 128GB · NVIDIA RTX 5090