M1 Pro 32GB vs NVIDIA RTX 5090 for local LLMs
2 reports on the M1 Pro 32GB and 126 on the NVIDIA RTX 5090
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the M1 Pro 32GB runs at 25.4 tokens per second (one run) and the NVIDIA RTX 5090 at 215.1 (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 8.8x higher on the NVIDIA RTX 5090 (205 GB/s on the M1 Pro 32GB, 1,792 on the NVIDIA RTX 5090).
- Memory
- 32GB unified
- Memory bandwidth
- 205 GB/s
- FP16 compute
- 5.2 TFLOPS
- Reports
- 2
- 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 | M1 Pro 32GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 25.4one runllama.cpp32K context | 215.1one 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 | M1 Pro 32GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.6 35B · 3B active | 40.7 t/sQ3_K_M | 163.0 t/sQ5_K_M |
| Qwen3.8 27B | 11.2 t/sQ4_K_S | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 20.3 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 11.2 t/sQ4_K_S | 44.9 t/sQ6_K |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
| Gemma 4 26B · 4B active | 24.6 t/sQ4_K_M | 114.5 t/sQ6_K |
Change the context, RAM or model in the calculator: M1 Pro 32GB · NVIDIA RTX 5090
Every report on each card, with its source: M1 Pro 32GB · NVIDIA RTX 5090