M4 16GB vs M6 32GB for local LLMs
5 reports on the M4 16GB and 2 on the M6 32GB
Which is faster for local LLMs?
On Gemma 4 26B · 4B active at 4-bit, the M4 16GB runs at 30.9 tokens per second (one run) and the M6 32GB at 52.2 (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 42% higher on the M6 32GB (120 GB/s on the M4 16GB, 171 on the M6 32GB).
- Memory
- 16GB unified
- Memory bandwidth
- 120 GB/s
- FP16 compute
- 4.3 TFLOPS
- Reports
- 5
- Memory
- 32GB unified
- Memory bandwidth
- 171 GB/s
- FP16 compute
- not on record
- Reports
- 2
Measured on both
Median tokens per second from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same quant level. Engines and context lengths can still differ between the runs. How to read these
| Model | M4 16GB | M6 32GB |
|---|---|---|
| Gemma 4 26B · 4B active4-bit | 30.9one run | 52.2one run |
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. Where a model was also measured above, the measurement wins.
| Model | M4 16GB | M6 32GB |
|---|---|---|
| Gemma 4 26B · 4B active | doesn't fit at these settings | 23.2 t/sQ4_K_M |
| Qwen3.8 27B | doesn't fit at these settings | 10.5 t/sQ4_K_S |
| 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 | doesn't fit at these settings | 38.2 t/sQ3_K_M |
| Qwen3.6 27B | doesn't fit at these settings | 10.5 t/sQ4_K_S |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M4 16GB · M6 32GB
Every report on each card, with its source: M4 16GB · M6 32GB