M4 16GB vs M5 32GB for local LLMs
26 reports on the M4 16GB and 4 on the M5 32GB
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 28% higher on the M5 32GB (120 GB/s on the M4 16GB, 154 on the M5 32GB). The estimates below compare them on the models people run most.
M4 16GB
- Memory
- 16GB unified
- Memory bandwidth
- 120 GB/s
- FP16 compute
- 4.3 TFLOPS
- Reports
- 26
M5 32GB
- Memory
- 32GB unified
- Memory bandwidth
- 154 GB/s
- FP16 compute
- not on record
- Reports
- 4
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 | M4 16GB | M5 32GB |
|---|---|---|
| Qwen3.8 27B | doesn't fit at these settings | 9.2 t/sQ4_K_S |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | doesn't fit at these settings | 33.5 t/sQ3_K_M |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | doesn't fit at these settings | 9.2 t/sQ4_K_S |
| Gemma 4 26B · 4B active | doesn't fit at these settings | 20.3 t/sQ4_K_M |
Change the context, RAM or model in the calculator: M4 16GB · M5 32GB
Every report on each card, with its source: M4 16GB · M5 32GB