M3 Max 128GB vs M3 Max 96GB for local LLMs
6 reports on the M3 Max 128GB and 2 on the M3 Max 96GB
Which is faster for local LLMs?
On Qwen3.6 27B at 8-bit, the M3 Max 128GB has generation speed not reported; prompt processing 160.0 tokens/s (one run); the M3 Max 96GB has 7.4 generation tokens/s (one run); prompt processing 121.3 tokens/s (one run). Memory bandwidth, which caps how fast a card can write, is 33% higher on the M3 Max 128GB (410 GB/s on the M3 Max 128GB, 307 on the M3 Max 96GB).
- Memory
- 128GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 14.2 TFLOPS
- Reports
- 6
- Memory
- 96GB unified
- Memory bandwidth
- 307 GB/s
- FP16 compute
- 10.6 TFLOPS
- Reports
- 2
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 Max 128GB | M3 Max 96GB |
|---|---|---|
| Qwen3.6 27B8-bit | -0 runsPP 160.0 (one run)MLX290K context | 7.4one runPP 121.3 (one run)oMLXcontext 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 Max 128GB | M3 Max 96GB |
|---|---|---|
| Qwen3.6 27B | 5.3 t/sFP16 | 4.3 t/sFP16 |
| Qwen3.8 27B | 5.3 t/sFP16 | 4.3 t/sFP16 |
| Qwen3.8 125B · 6B active | 24.3 t/sQ5_K_S | 29.7 t/sQ3_K_M |
| DeepSeek V4 Flash 284B · 13B active | 38.2 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 16.8 t/sFP16 | 30.8 t/sQ8_0 |
| Gemma 4 26B · 4B active | 14.4 t/sFP16 | 10.2 t/sFP16 |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M3 Max 128GB · M3 Max 96GB
Every report on each card, with its source: M3 Max 128GB · M3 Max 96GB