M5 32GB vs M6 24GB for local LLMs
3 reports on the M5 32GB and 0 on the M6 24GB
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 11% higher on the M6 24GB (154 GB/s on the M5 32GB, 171 on the M6 24GB). The estimates below compare them on the models people run most.
M5 32GB
- Memory
- 32GB unified
- Memory bandwidth
- 154 GB/s
- FP16 compute
- not on record
- Reports
- 3
M6 24GB
- Memory
- 24GB unified
- Memory bandwidth
- 171 GB/s
- FP16 compute
- not on record
- Reports
- 0
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 32GB | M6 24GB |
|---|---|---|
| Qwen3.8 27B | 9.2 t/sQ4_K_S | 16.8 t/sQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 33.5 t/sQ3_K_M | 55.5 t/sQ2_K |
| Qwen3.6 27B | 9.2 t/sQ4_K_S | 16.8 t/sQ2_K |
| Gemma 4 26B · 4B active | 20.3 t/sQ4_K_M | 37.4 t/sQ3_K_S |
Change the context, RAM or model in the calculator: M5 32GB · M6 24GB
Every report on each card, with its source: M5 32GB · M6 24GB