M5 Max 128GB vs NVIDIA RTX 3060 12GB for local LLMs
48 reports on the M5 Max 128GB and 65 on the NVIDIA RTX 3060 12GB
Which is faster for local LLMs?
On Gemma 4 5.1B at 4-bit, the M5 Max 128GB has 205.0 generation tokens/s (one run); the NVIDIA RTX 3060 12GB has 60.0 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 1.7x higher on the M5 Max 128GB (614 GB/s on the M5 Max 128GB, 360 on the NVIDIA RTX 3060 12GB).
- Memory
- 128GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 48
- Memory
- 12GB
- Memory bandwidth
- 360 GB/s
- FP16 compute
- 51 TFLOPS
- Reports
- 65
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 | M5 Max 128GB | NVIDIA RTX 3060 12GB |
|---|---|---|
| Gemma 4 5.1B4-bit | 205.0one runmlx-vlm4K context | 60.0one runOllamacontext 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 | M5 Max 128GB | NVIDIA RTX 3060 12GB |
|---|---|---|
| Gemma 4 5.1B | 47.9 t/sFP16 | 38.8 t/sQ8_0 |
| Qwen3.8 27B | 9.0 t/sFP16 | 1.5 t/sQ8_0, layers on CPU |
| Qwen3.8 125B · 6B active | 41.2 t/sQ5_K_S | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 28.5 t/sFP16 | 13.1 t/sQ6_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 64.8 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 9.0 t/sFP16 | 1.5 t/sQ8_0, layers on CPU |
| Gemma 4 26B · 4B active | 24.4 t/sFP16 | 58.8 t/sQ2_K |
Change the context, RAM or model in the calculator: M5 Max 128GB · NVIDIA RTX 3060 12GB
Every report on each card, with its source: M5 Max 128GB · NVIDIA RTX 3060 12GB