M4 16GB vs M5 Ultra 256GB for local LLMs
26 reports on the M4 16GB and 31 on the M5 Ultra 256GB
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 10.2x higher on the M5 Ultra 256GB (120 GB/s on the M4 16GB, 1,229 on the M5 Ultra 256GB). 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 Ultra 256GB
- Memory
- 256GB unified
- Memory bandwidth
- 1,229 GB/s
- FP16 compute
- not on record
- Reports
- 31
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 Ultra 256GB |
|---|---|---|
| Qwen3.8 27B | doesn't fit at these settings | 14.9 t/sFP16 |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 50.8 t/sQ8_0 |
| Qwen3.6 35B · 3B active | doesn't fit at these settings | 53.5 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 66.9 t/sQ4_K_M |
| Qwen3.6 27B | doesn't fit at these settings | 14.9 t/sFP16 |
| Gemma 4 26B · 4B active | doesn't fit at these settings | 40.1 t/sFP16 |
Change the context, RAM or model in the calculator: M4 16GB · M5 Ultra 256GB
Every report on each card, with its source: M4 16GB · M5 Ultra 256GB