M6 32GB vs AMD RX 7900 XTX for local LLMs
2 reports on the M6 32GB and 28 on the AMD RX 7900 XTX
Which is faster for local LLMs?
On Gemma 4 26B · 4B active at 4-bit, the M6 32GB runs at 52.2 tokens per second (one run) and the AMD RX 7900 XTX at 142.8 (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 5.6x higher on the AMD RX 7900 XTX (171 GB/s on the M6 32GB, 960 on the AMD RX 7900 XTX).
- Memory
- 32GB unified
- Memory bandwidth
- 171 GB/s
- FP16 compute
- not on record
- Reports
- 2
- Memory
- 24GB
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 123 TFLOPS
- Reports
- 28
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 | M6 32GB | AMD RX 7900 XTX |
|---|---|---|
| Gemma 4 26B · 4B active4-bit | 52.2one run | 142.8one 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 | M6 32GB | AMD RX 7900 XTX |
|---|---|---|
| Gemma 4 26B · 4B active | 23.2 t/sQ4_K_M | 78.4 t/sQ5_K_S |
| Qwen3.8 27B | 10.5 t/sQ4_K_S | 34.8 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 19.5 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 38.2 t/sQ3_K_M | 123.2 t/sQ4_K_S |
| Qwen3.6 27B | 10.5 t/sQ4_K_S | 34.8 t/sQ4_K_M |
| 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: M6 32GB · AMD RX 7900 XTX
Every report on each card, with its source: M6 32GB · AMD RX 7900 XTX