M2 Mac with 8 GB vs M3 Mac with 8 GB
The M2 Mac with 8 GB runs Qwen3.5 2B about 88% faster than the M3 Mac with 8 GB (44 vs 23 tokens per second) and starts answering 4.1 s sooner.
Every model both run
| Model | M2 Mac with 8 GB | M3 Mac with 8 GB |
|---|---|---|
| Qwen3.5 2B | 44 tok/sfirst word 9.6 s | 23 tok/sfirst word 13.7 s |
Every model on the M2 Mac with 8 GBEvery model on the M3 Mac with 8 GBCompare other devices
Questions
- Is the M2 Mac with 8 GB faster than the M3 Mac with 8 GB for AI?
- The M2 Mac with 8 GB is faster on 1 of the the one model both run in Loci. The M2 Mac with 8 GB runs Qwen3.5 2B about 88% faster than the M3 Mac with 8 GB (44 vs 23 tokens per second) and starts answering 4.1 s sooner.
- Which runs Qwen3.5 2B faster, the M2 Mac with 8 GB or the M3 Mac with 8 GB?
- The M2 Mac with 8 GB runs Qwen3.5 2B about 88% faster than the M3 Mac with 8 GB (44 vs 23 tokens per second) and starts answering 4.1 s sooner.
Last 30 days, through · updated daily
How these speeds are measured
- Every number comes from real chats in Loci, timed on the device that wrote the answer, with Loci's default settings.
- Tokens per second is how fast an answer is written once it starts. On phones, four characters of text count as one token for every model; on a Mac, Loci counts the model's own tokens. Reading pace is about 5.
- First word is how long an answer takes to start after you send a message. Longer conversations take longer.
- Each device counts once. The large number is the median; the typical range covers the middle half of devices.
- Each phone speed comes from at least 10 phones. Fewer Macs run Loci, so each Mac speed says how many Macs it comes from.
- On phones, answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out.