TEST #2940 RESULTS
03/01/2026 - 2:34 PM
ACCELERATOR
MODEL
72.5
tokens/s
generation
1.08
sec
time to first token
1078
tokens/s
prompt
417
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
16GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:49 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1325
tokens/s
85.5
tokens/s
785
ms
pp4096+tg256
1199
tokens/s
50.9
tokens/s
3.44
sec
pp2048+tg256
1364
tokens/s
61.8
tokens/s
1.52
sec
pp2048+tg768
1255
tokens/s
62.1
tokens/s
1.65
sec
pp1024+tg1024
1353
tokens/s
75.4
tokens/s
768
ms
pp1280+tg3072
1379
tokens/s
56.7
tokens/s
940
ms
pp384+tg1152
1063
tokens/s
79.3
tokens/s
371
ms
pp64+tg1024
537
tokens/s
89.3
tokens/s
136
ms
pp16+tg1536
229
tokens/s
91.4
tokens/s
79
ms