Apple M1 4P+4E+8GPU
GPU
8
GB
PERFORMANCE OVERVIEW
Model
Qwen3 0.6B
Q4_K - Medium752M
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Prompt Speed
912tokens/s
607tokens/s
134tokens/s
Generation Speed
47.5tokens/s
40.4tokens/s
14.6tokens/s
Time to First Token
1.47sec
2.17sec
9.65sec
LocalScore
309
225
59
COMPARE MODELS
3 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Qwen3 0.6B
Q4_K - Medium