M4 Max 128GB vs NVIDIA RTX 5060 8GB for local LLMs
52 reports on the M4 Max 128GB and 5 on the NVIDIA RTX 5060 8GB
Which is faster for local LLMs?
On Qwen3.8 27B at 2-bit, the M4 Max 128GB has 24.5 generation tokens/s (2 runs); prompt processing 251.4 tokens/s (2 runs); the NVIDIA RTX 5060 8GB has 30.1 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 22% higher on the M4 Max 128GB (546 GB/s on the M4 Max 128GB, 448 on the NVIDIA RTX 5060 8GB).
- Memory
- 128GB unified
- Memory bandwidth
- 546 GB/s
- FP16 compute
- 18.4 TFLOPS
- Reports
- 52
- Memory
- 8GB
- Memory bandwidth
- 448 GB/s
- FP16 compute
- 76 TFLOPS
- Reports
- 5
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 | M4 Max 128GB | NVIDIA RTX 5060 8GB |
|---|---|---|
| Qwen3.8 27B2-bit | 24.52 runsPP 251.4 (2 runs)llama.cppcontext not stated | 30.1one runllama.cpp8K context |
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 | M4 Max 128GB | NVIDIA RTX 5060 8GB |
|---|---|---|
| Qwen3.8 27B | 6.7 t/sFP16 | 1.8 t/sQ6_K, layers on CPU |
| Qwen3.8 125B · 6B active | 30.7 t/sQ5_K_S | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 21.2 t/sFP16 | 16.1 t/sQ5_K_M, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 48.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 6.7 t/sFP16 | 1.8 t/sQ6_K, layers on CPU |
| Gemma 4 26B · 4B active | 18.2 t/sFP16 | 10.2 t/sQ6_K, experts in RAM |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M4 Max 128GB · NVIDIA RTX 5060 8GB
Every report on each card, with its source: M4 Max 128GB · NVIDIA RTX 5060 8GB