M2 Max 64GB vs M3 Ultra 256GB for local LLMs
20 reports on the M2 Max 64GB and 15 on the M3 Ultra 256GB
Which is faster for local LLMs?
On Qwen3.5 9B at 4-bit, the M2 Max 64GB has 62.7 generation tokens/s (one run); prompt processing 321.2 tokens/s (one run); the M3 Ultra 256GB has 107.5 generation 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 2.0x higher on the M3 Ultra 256GB (410 GB/s on the M2 Max 64GB, 819 on the M3 Ultra 256GB).
- Memory
- 64GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 20
- Memory
- 256GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 28.4 TFLOPS
- Reports
- 15
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 | M2 Max 64GB | M3 Ultra 256GB |
|---|---|---|
| Qwen3.5 9B4-bit | 62.7one runPP 321.2 (one run)MLXcontext not stated | 107.5one 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 | M2 Max 64GB | M3 Ultra 256GB |
|---|---|---|
| Qwen3.5 9B | 15.7 t/sFP16 | 23.9 t/sFP16 |
| Qwen3.8 27B | 10.4 t/sQ8_0 | 8.0 t/sFP16 |
| Qwen3.8 125B · 6B active | 47.5 t/sQ2_K | 27.3 t/sQ8_0 |
| Qwen3.6 35B · 3B active | 32.9 t/sQ8_0 | 28.7 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 36.0 t/sQ4_K_M |
| Qwen3.6 27B | 10.4 t/sQ8_0 | 8.0 t/sFP16 |
| Gemma 4 26B · 4B active | 28.2 t/sQ8_0 | 21.5 t/sFP16 |
Change the context, RAM or model in the calculator: M2 Max 64GB · M3 Ultra 256GB
Every report on each card, with its source: M2 Max 64GB · M3 Ultra 256GB