M2 Max 32GB vs NVIDIA Tesla P40 24GB for local LLMs
3 reports on the M2 Max 32GB and 12 on the NVIDIA Tesla P40 24GB
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the M2 Max 32GB has 39.3 generation tokens/s (2 runs); prompt processing 671.4 tokens/s (one run); the NVIDIA Tesla P40 24GB has 9.7 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 18% higher on the M2 Max 32GB (410 GB/s on the M2 Max 32GB, 346 on the NVIDIA Tesla P40 24GB). Across 2 shared models with generation measurements on both cards, the M2 Max 32GB's median is higher on 2 and the NVIDIA Tesla P40 24GB's on 0.
- Memory
- 32GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 3
- Memory
- 24GB
- Memory bandwidth
- 346 GB/s
- FP16 compute
- 12 TFLOPS
- Reports
- 12
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 32GB | NVIDIA Tesla P40 24GB |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 39.32 runsPP 671.4 (one run)llama.cpp, 1 not stated4K to 60K context | 9.7one runengine not statedcontext not stated |
| Ornith1.5 35B · 3B active4-bit | 108.0one runoMLXcontext not stated | 60.8one runPP 1104.0 (one run)llama.cppcontext 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 | M2 Max 32GB | NVIDIA Tesla P40 24GB |
|---|---|---|
| Qwen3.6 35B · 3B active | 76.1 t/sQ3_K_M | 44.4 t/sQ4_K_S |
| Ornith1.5 35B · 3B active | 76.1 t/sQ3_K_M | 44.4 t/sQ4_K_S |
| Qwen3.8 27B | 20.9 t/sQ4_K_S | 12.5 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 16.9 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 20.9 t/sQ4_K_S | 12.5 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 46.1 t/sQ4_K_M | 28.2 t/sQ5_K_S |
Change the context, RAM or model in the calculator: M2 Max 32GB · NVIDIA Tesla P40 24GB
Every report on each card, with its source: M2 Max 32GB · NVIDIA Tesla P40 24GB