TEST #3031 RESULTS
03/07/2026 - 11:12 PM
ACCELERATOR
MODEL
66.8
tokens/s
generation
1.11
sec
time to first token
1079
tokens/s
prompt
402
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q5_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
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 Jan 19 22:00:55 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1223
tokens/s
70.2
tokens/s
851
ms
pp4096+tg256
1139
tokens/s
47.7
tokens/s
3.62
sec
pp2048+tg256
1282
tokens/s
59.5
tokens/s
1.61
sec
pp2048+tg768
1259
tokens/s
59.9
tokens/s
1.64
sec
pp1024+tg1024
1327
tokens/s
69.3
tokens/s
785
ms
pp1280+tg3072
1311
tokens/s
57.1
tokens/s
990
ms
pp384+tg1152
1240
tokens/s
76.6
tokens/s
321
ms
pp64+tg1024
698
tokens/s
82.3
tokens/s
103
ms
pp16+tg1536
235
tokens/s
79.1
tokens/s
79
ms