M3 Ultra 256GB vs M5 Max 128GB for local LLMs
8 reports on the M3 Ultra 256GB and 32 on the M5 Max 128GB
Which is faster for local LLMs?
On Qwen3.8 125B · 6B active at 4-bit, the M3 Ultra 256GB runs at 25.7 tokens per second (one run) and the M5 Max 128GB at 55.0 (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 33% higher on the M3 Ultra 256GB (819 GB/s on the M3 Ultra 256GB, 614 on the M5 Max 128GB).
- Memory
- 256GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 28.4 TFLOPS
- Reports
- 8
- Memory
- 128GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 32
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 bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | M3 Ultra 256GB | M5 Max 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active4-bit | 25.7one runengine not stated128 context | 55.0one runengine not statedcontext not stated |
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 | M3 Ultra 256GB | M5 Max 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active | 27.3 t/sQ8_0 | 41.2 t/sQ5_K_S |
| Qwen3.8 27B | 8.0 t/sFP16 | 9.0 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 36.0 t/sQ4_K_M | 64.8 t/sQ2_K |
| Qwen3.6 35B · 3B active | 28.7 t/sFP16 | 28.5 t/sFP16 |
| Qwen3.6 27B | 8.0 t/sFP16 | 9.0 t/sFP16 |
| GLM-5.3 320B · 18B active | 19.1 t/sQ3_K_M | doesn't fit at these settings |
| Gemma 4 26B · 4B active | 21.5 t/sFP16 | 24.4 t/sFP16 |
Change the context, RAM or model in the calculator: M3 Ultra 256GB · M5 Max 128GB
Every report on each card, with its source: M3 Ultra 256GB · M5 Max 128GB