M2 Max 64GB vs M3 Ultra 512GB for local LLMs
20 reports on the M2 Max 64GB and 41 on the M3 Ultra 512GB
Which is faster for local LLMs?
On Gemma 4 26B · 4B active at 4-bit, the M2 Max 64GB has 61.6 generation tokens/s (one run); prompt processing 465.2 tokens/s (one run); the M3 Ultra 512GB has 87.8 generation tokens/s (one run); prompt processing 2595.3 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 2.0x higher on the M3 Ultra 512GB (410 GB/s on the M2 Max 64GB, 819 on the M3 Ultra 512GB). Across 2 shared models with generation measurements on both cards, the M2 Max 64GB's median is higher on 1 and the M3 Ultra 512GB's on 1.
- Memory
- 64GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 20
- Memory
- 512GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 28.4 TFLOPS
- Reports
- 41
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 512GB |
|---|---|---|
| Gemma 4 26B · 4B active4-bit | 61.6one runPP 465.2 (one run)MLXcontext not stated | 87.8one runPP 2595.3 (one run)llama.cppcontext not stated |
| Qwen3.5 35B · 3B active4-bit | 88.9one runPP 521.5 (one run)MLXcontext not stated | 80.9one runPP 2779.0 (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 | M2 Max 64GB | M3 Ultra 512GB |
|---|---|---|
| Gemma 4 26B · 4B active | 28.2 t/sQ8_0 | 21.5 t/sFP16 |
| Qwen3.5 35B · 3B active | 32.9 t/sQ8_0 | 28.7 t/sFP16 |
| Qwen3.8 27B | 10.4 t/sQ8_0 | 8.0 t/sFP16 |
| Qwen3.8 125B · 6B active | 47.5 t/sQ2_K | 13.6 t/sFP16 |
| 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 | 22.6 t/sQ8_0 |
| Qwen3.6 27B | 10.4 t/sQ8_0 | 8.0 t/sFP16 |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | 30.0 t/sQ4_K_M |
Change the context, RAM or model in the calculator: M2 Max 64GB · M3 Ultra 512GB
Every report on each card, with its source: M2 Max 64GB · M3 Ultra 512GB