M4 24GB vs AMD RX 9070 XT 16GB for local LLMs
3 reports on the M4 24GB and 12 on the AMD RX 9070 XT 16GB
Which is faster for local LLMs?
On Qwen3.5 9B at 4-bit, the M4 24GB runs at 17.4 tokens per second (one run) and the AMD RX 9070 XT 16GB at 7.9 (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 5.3x higher on the AMD RX 9070 XT 16GB (120 GB/s on the M4 24GB, 640 on the AMD RX 9070 XT 16GB).
- Memory
- 24GB unified
- Memory bandwidth
- 120 GB/s
- FP16 compute
- 4.3 TFLOPS
- Reports
- 3
- Memory
- 16GB
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 195 TFLOPS
- Reports
- 12
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 24GB | AMD RX 9070 XT 16GB |
|---|---|---|
| Qwen3.5 9B4-bit | 17.4one run | 7.9one 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 24GB | AMD RX 9070 XT 16GB |
|---|---|---|
| Qwen3.5 9B | 10.1 t/sQ8_0 | 39.1 t/sQ8_0 |
| Qwen3.8 27B | 10.8 t/sQ2_K | 41.7 t/sQ2_K |
| 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 | 35.8 t/sQ2_K | 138.0 t/sQ2_K |
| Qwen3.6 27B | 10.8 t/sQ2_K | 41.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 24.1 t/sQ3_K_S | 93.0 t/sQ3_K_S |
Change the context, RAM or model in the calculator: M4 24GB · AMD RX 9070 XT 16GB
Every report on each card, with its source: M4 24GB · AMD RX 9070 XT 16GB