M2 Max 64GB vs M5 Max 48GB for local LLMs
20 reports on the M2 Max 64GB and 67 on the M5 Max 48GB
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the M2 Max 64GB has 77.5 generation tokens/s (2 runs); the M5 Max 48GB has 137.7 generation tokens/s (2 runs); prompt processing 3338.1 tokens/s (2 runs). 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 50% higher on the M5 Max 48GB (410 GB/s on the M2 Max 64GB, 614 on the M5 Max 48GB). Across 7 shared models with generation measurements on both cards, the M2 Max 64GB's median is higher on 0 and the M5 Max 48GB's on 7.
- Memory
- 64GB unified
- Memory bandwidth
- 410 GB/s
- FP16 compute
- 13.6 TFLOPS
- Reports
- 20
- Memory
- 48GB unified
- Memory bandwidth
- 614 GB/s
- FP16 compute
- not on record
- Reports
- 67
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 64GB | M5 Max 48GB |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 77.52 runsLM Studio, Ollama32K to 256K context | 137.72 runsPP 3338.1 (2 runs)llama.cpp, MLXcontext not stated |
| Qwen 2.5 Coder 32B4-bit | 18.0one runPP 126.8 (one run)MLXcontext not stated | 27.42 runsPP 709.7 (2 runs)llama.cpp, MLXcontext not stated |
| Gemma 4 26B · 4B active4-bit | 61.6one runPP 465.2 (one run)MLXcontext not stated | 116.9one runPP 3423.2 (one run)llama.cppcontext not stated |
| Qwen3.5 9B4-bit | 62.7one runPP 321.2 (one run)MLXcontext not stated | 86.5one runPP 2369.3 (one run)llama.cppcontext not stated |
| Qwen3.5 4B4-bit | 70.4one runTransformerscontext not stated | 135.6one runPP 4099.7 (one run)llama.cppcontext not stated |
| Qwen3.5 27B4-bit | 20.7one runPP 91.4 (one run)MLXcontext not stated | 29.2one runPP 730.5 (one run)llama.cppcontext not stated |
| Qwen3.5 35B · 3B active4-bit | 88.9one runPP 521.5 (one run)MLXcontext not stated | 111.2one runPP 3378.3 (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 64GB | M5 Max 48GB |
|---|---|---|
| Qwen3.6 35B · 3B active | 32.9 t/sQ8_0 | 88.4 t/sQ5_K_M |
| Qwen 2.5 Coder 32B | 10.8 t/sQ6_K | 24.4 t/sQ5_K_S |
| Gemma 4 26B · 4B active | 28.2 t/sQ8_0 | 43.2 t/sQ8_0 |
| Qwen3.5 9B | 15.7 t/sFP16 | 27.1 t/sFP16 |
| Qwen3.5 4B | 35.2 t/sFP16 | 61.0 t/sFP16 |
| Qwen3.5 27B | 10.4 t/sQ8_0 | 22.3 t/sQ6_K |
| Qwen3.5 35B · 3B active | 32.9 t/sQ8_0 | 88.4 t/sQ5_K_M |
| Qwen3.8 27B | 10.4 t/sQ8_0 | 22.3 t/sQ6_K |
| Qwen3.8 125B · 6B active | 47.5 t/sQ2_K | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 10.4 t/sQ8_0 | 22.3 t/sQ6_K |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: M2 Max 64GB · M5 Max 48GB
Every report on each card, with its source: M2 Max 64GB · M5 Max 48GB