M5 Ultra 256GB vs NVIDIA RTX 5060 Ti 16GB for local LLMs
31 reports on the M5 Ultra 256GB and 72 on the NVIDIA RTX 5060 Ti 16GB
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 2.7x higher on the M5 Ultra 256GB (1,229 GB/s on the M5 Ultra 256GB, 448 on the NVIDIA RTX 5060 Ti 16GB). The estimates below compare them on the models people run most.
- Memory
- 256GB unified
- Memory bandwidth
- 1,229 GB/s
- FP16 compute
- not on record
- Reports
- 31
- Memory
- 16GB
- Memory bandwidth
- 448 GB/s
- FP16 compute
- 95 TFLOPS
- Reports
- 72
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 | M5 Ultra 256GB | NVIDIA RTX 5060 Ti 16GB |
|---|---|---|
| Qwen3.8 27B | 14.9 t/sFP16 | 29.2 t/sQ2_K |
| Qwen3.8 125B · 6B active | 50.8 t/sQ8_0 | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 53.5 t/sFP16 | 96.6 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | 66.9 t/sQ4_K_M | doesn't fit at these settings |
| Qwen3.6 27B | 14.9 t/sFP16 | 29.2 t/sQ2_K |
| Gemma 4 26B · 4B active | 40.1 t/sFP16 | 65.1 t/sQ3_K_S |
Change the context, RAM or model in the calculator: M5 Ultra 256GB · NVIDIA RTX 5060 Ti 16GB
Every report on each card, with its source: M5 Ultra 256GB · NVIDIA RTX 5060 Ti 16GB