M2 Max 96GB vs NVIDIA RTX 5080 for local LLMs
7 reports on the M2 Max 96GB and 27 on the NVIDIA RTX 5080
Which is faster for local LLMs?
On Qwen3 8B at 4-bit, the M2 Max 96GB has 43.0 generation tokens/s (one run); the NVIDIA RTX 5080 has 130.6 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 2.3x higher on the NVIDIA RTX 5080 (410 GB/s on the M2 Max 96GB, 960 on the NVIDIA RTX 5080).
- Memory
- 96GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 7
- Memory
- 16GB
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 225 TFLOPS
- Reports
- 27
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 96GB | NVIDIA RTX 5080 |
|---|---|---|
| Qwen3 8B4-bit | 43.0one runOllamacontext not stated | 130.6one runllama.cpp40K 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 | M2 Max 96GB | NVIDIA RTX 5080 |
|---|---|---|
| Qwen3 8B | 17.6 t/sFP16 | 81.2 t/sQ6_K |
| Qwen3.8 27B | 5.2 t/sFP16 | 62.6 t/sQ2_K |
| Qwen3.8 125B · 6B active | 36.2 t/sQ3_K_M | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 37.6 t/sQ8_0 | 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 | 5.2 t/sFP16 | 62.6 t/sQ2_K |
| Gemma 4 26B · 4B active | 12.5 t/sFP16 | 139.6 t/sQ3_K_S |
Change the context, RAM or model in the calculator: M2 Max 96GB · NVIDIA RTX 5080
Every report on each card, with its source: M2 Max 96GB · NVIDIA RTX 5080