M5 Max 48GB vs M5 Pro 48GB for local LLMs
67 reports on the M5 Max 48GB and 9 on the M5 Pro 48GB
Which is faster for local LLMs?
On Qwen3.5 27B at 4-bit, the M5 Max 48GB has 29.2 generation tokens/s (one run); prompt processing 730.5 tokens/s (one run); the M5 Pro 48GB has generation speed not reported; prompt processing 461.0 tokens/s (one run). Memory bandwidth, which caps how fast a card can write, is 2.0x higher on the M5 Max 48GB (614 GB/s on the M5 Max 48GB, 307 on the M5 Pro 48GB).
- Memory
- 48GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 67
- Memory
- 48GB unified
- Memory bandwidth
- 307 GB/s
- FP16 compute
- not on record
- Reports
- 9
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 | M5 Max 48GB | M5 Pro 48GB |
|---|---|---|
| Qwen3.5 27B4-bit | 29.2one runPP 730.5 (one run)llama.cppcontext not stated | -0 runsPP 461.0 (one run)engine not stated4K context |
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 | M5 Max 48GB | M5 Pro 48GB |
|---|---|---|
| Qwen3.5 27B | 22.3 t/sQ6_K | 12.0 t/sQ6_K |
| Qwen3.8 27B | 22.3 t/sQ6_K | 12.0 t/sQ6_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 88.4 t/sQ5_K_M | 47.5 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 | 22.3 t/sQ6_K | 12.0 t/sQ6_K |
| Gemma 4 26B · 4B active | 43.2 t/sQ8_0 | 23.2 t/sQ8_0 |
Change the context, RAM or model in the calculator: M5 Max 48GB · M5 Pro 48GB
Every report on each card, with its source: M5 Max 48GB · M5 Pro 48GB