M2 24GB vs M4 16GB for local LLMs
0 reports on the M2 24GB and 5 on the M4 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 17% higher on the M4 16GB (102 GB/s on the M2 24GB, 120 on the M4 16GB). The estimates below compare them on the models people run most.
M2 24GB
- Memory
- 24GB unified
- Memory bandwidth
- 102 GB/s
- FP16 compute
- 3.6 TFLOPS
- Reports
- 0
M4 16GB
- Memory
- 16GB unified
- Memory bandwidth
- 120 GB/s
- FP16 compute
- 4.3 TFLOPS
- Reports
- 5
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 | M2 24GB | M4 16GB |
|---|---|---|
| Qwen3.8 27B | 9.8 t/sQ2_K | doesn't fit at these settings |
| 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 | 32.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 9.8 t/sQ2_K | doesn't fit at these settings |
| Gemma 4 26B · 4B active | 21.8 t/sQ3_K_S | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M2 24GB · M4 16GB
Every report on each card, with its source: M2 24GB · M4 16GB