Accelerator icon
Apple M1 Max 8P+2E+32GPU
GPU
64
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Granite 3.2 8b Instruct
Q4_K - Medium8.4B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
2060tokens/s
332tokens/s
179tokens/s
Generation Speed
124tokens/s
32.6tokens/s
17.8tokens/s
Time to First Token
552ms
3.64sec
6.79sec
LocalScore
774
144
78
COMPARE MODELS

4 models tested

Select Models

Llama 3.2 1B Instruct

Q4_K - Medium

Qwen2.5 14B Instruct

Q4_K - Medium

Granite 3.2 8b Instruct

Q4_K - Medium

Qwen3 Embedding 0.6b

Q8_0

Apple M1 Max 8P+2E+32GPU - 64GB