TEST #2936 RESULTS
02/27/2026 - 11:05 PM
ACCELERATOR
MODEL
123
tokens/s
generation
551
ms
time to first token
2049
tokens/s
prompt
771
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Max 8P+4E
RAM
32GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:30 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2708
tokens/s
152
tokens/s
385
ms
pp4096+tg256
2469
tokens/s
93.8
tokens/s
1.67
sec
pp2048+tg256
2679
tokens/s
123
tokens/s
772
ms
pp2048+tg768
2675
tokens/s
118
tokens/s
774
ms
pp1024+tg1024
2305
tokens/s
127
tokens/s
452
ms
pp1280+tg3072
2215
tokens/s
101
tokens/s
587
ms
pp384+tg1152
2238
tokens/s
128
tokens/s
178
ms
pp64+tg1024
893
tokens/s
134
tokens/s
77
ms
pp16+tg1536
255
tokens/s
133
tokens/s
68
ms