M2 8GB vs M3 8GB for local LLMs
3 reports on the M2 8GB and 0 on the M3 8GB
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 about the same on both (102 GB/s on the M2 8GB, 102 on the M3 8GB). The estimates below compare them on the models people run most.
M2 8GB
- Memory
- 8GB unified
- Memory bandwidth
- 102 GB/s
- FP16 compute
- 3.6 TFLOPS
- Reports
- 3
M3 8GB
- Memory
- 8GB unified
- Memory bandwidth
- 102 GB/s
- FP16 compute
- 4.1 TFLOPS
- 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 | M2 8GB | M3 8GB |
|---|---|---|
| Qwen3.8 27B | doesn't fit at these settings | doesn't fit at these settings |
| 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 | 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 27B | doesn't fit at these settings | doesn't fit at these settings |
| Gemma 4 26B · 4B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M2 8GB · M3 8GB
Every report on each card, with its source: M2 8GB · M3 8GB