M4 Max 128GB vs NVIDIA RTX 5080 for local LLMs
52 reports on the M4 Max 128GB and 26 on the NVIDIA RTX 5080
Which is faster for local LLMs?
On gpt-oss 21B · 3.6B active at 4-bit, the M4 Max 128GB has 123.1 generation tokens/s (one run); prompt processing 1577.0 tokens/s (one run); the NVIDIA RTX 5080 has 178.3 generation tokens/s (one run); prompt processing 10328.6 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 1.8x higher on the NVIDIA RTX 5080 (546 GB/s on the M4 Max 128GB, 960 on the NVIDIA RTX 5080).
- Memory
- 128GB unified
- Memory bandwidth
- 546 GB/s
- FP16 compute
- 18.4 TFLOPS
- Reports
- 52
- 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 | M4 Max 128GB | NVIDIA RTX 5080 |
|---|---|---|
| gpt-oss 21B · 3.6B active4-bit | 123.1one runPP 1577.0 (one run)llama.cppcontext not stated | 178.3one runPP 10328.6 (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 | M4 Max 128GB | NVIDIA RTX 5080 |
|---|---|---|
| gpt-oss 21B · 3.6B active | 40.5 t/sFP16 | 223.1 t/sQ4_K_S |
| Qwen3.8 27B | 6.7 t/sFP16 | 62.6 t/sQ2_K |
| 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 | 207.0 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | 48.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 6.7 t/sFP16 | 62.6 t/sQ2_K |
| Gemma 4 26B · 4B active | 18.2 t/sFP16 | 139.6 t/sQ3_K_S |
Change the context, RAM or model in the calculator: M4 Max 128GB · NVIDIA RTX 5080
Every report on each card, with its source: M4 Max 128GB · NVIDIA RTX 5080