M5 Max 48GB vs NVIDIA RTX 5080 for local LLMs
67 reports on the M5 Max 48GB and 26 on the NVIDIA RTX 5080
Which is faster for local LLMs?
On Llama 3.2 3B at 4-bit, the M5 Max 48GB has 199.9 generation tokens/s (one run); prompt processing 6122.5 tokens/s (one run); the NVIDIA RTX 5080 has 298.6 generation tokens/s (one run); prompt processing 19397.4 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 1.6x higher on the NVIDIA RTX 5080 (614 GB/s on the M5 Max 48GB, 960 on the NVIDIA RTX 5080).
- Memory
- 48GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 67
- Memory
- 16GB
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 225 TFLOPS
- Reports
- 26
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 48GB | NVIDIA RTX 5080 |
|---|---|---|
| Llama 3.2 3B4-bit | 199.9one runPP 6122.5 (one run)llama.cppcontext not stated | 298.6one runPP 19397.4 (one run)Ollama16K 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 | M5 Max 48GB | NVIDIA RTX 5080 |
|---|---|---|
| Llama 3.2 3B | 81.4 t/sFP16 | 88.0 t/sFP16 |
| Qwen3.8 27B | 22.3 t/sQ6_K | 62.6 t/sQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 88.4 t/sQ5_K_M | 207.0 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 22.3 t/sQ6_K | 62.6 t/sQ2_K |
| Gemma 4 26B · 4B active | 43.2 t/sQ8_0 | 139.6 t/sQ3_K_S |
Change the context, RAM or model in the calculator: M5 Max 48GB · NVIDIA RTX 5080
Every report on each card, with its source: M5 Max 48GB · NVIDIA RTX 5080