M3 Ultra 256GB vs M5 Max 48GB for local LLMs
15 reports on the M3 Ultra 256GB and 67 on the M5 Max 48GB
Which is faster for local LLMs?
On Qwen3.5 9B at 4-bit, the M3 Ultra 256GB has 107.5 generation tokens/s (one run); the M5 Max 48GB has 86.5 generation tokens/s (one run); prompt processing 2369.3 tokens/s (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 48GB).
- Memory
- 256GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 28.4 TFLOPS
- Reports
- 15
- Memory
- 48GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 67
Measured on both
Generation and prompt processing speeds 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 48GB |
|---|---|---|
| Qwen3.5 9B4-bit | 107.5one runengine not statedcontext not stated | 86.5one runPP 2369.3 (one run)llama.cppcontext 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 48GB |
|---|---|---|
| Qwen3.5 9B | 23.9 t/sFP16 | 27.1 t/sFP16 |
| Qwen3.8 27B | 8.0 t/sFP16 | 22.3 t/sQ6_K |
| Qwen3.8 125B · 6B active | 27.3 t/sQ8_0 | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 28.7 t/sFP16 | 88.4 t/sQ5_K_M |
| DeepSeek V4 Flash 284B · 13B active | 36.0 t/sQ4_K_M | doesn't fit at these settings |
| Qwen3.6 27B | 8.0 t/sFP16 | 22.3 t/sQ6_K |
| Gemma 4 26B · 4B active | 21.5 t/sFP16 | 43.2 t/sQ8_0 |
Change the context, RAM or model in the calculator: M3 Ultra 256GB · M5 Max 48GB
Every report on each card, with its source: M3 Ultra 256GB · M5 Max 48GB