TEST #3440 RESULTS
05/04/2026 - 6:17 PM
ACCELERATOR
MODEL
90.9
tokens/s
generation
908
ms
time to first token
1305
tokens/s
prompt
507
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 6P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:31:17 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1635
tokens/s
104
tokens/s
636
ms
pp4096+tg256
1379
tokens/s
60.6
tokens/s
2.99
sec
pp2048+tg256
1559
tokens/s
82.5
tokens/s
1.33
sec
pp2048+tg768
1561
tokens/s
78.8
tokens/s
1.32
sec
pp1024+tg1024
1600
tokens/s
93.3
tokens/s
650
ms
pp1280+tg3072
1602
tokens/s
73.9
tokens/s
809
ms
pp384+tg1152
1457
tokens/s
104
tokens/s
272
ms
pp64+tg1024
658
tokens/s
113
tokens/s
105
ms
pp16+tg1536
293
tokens/s
108
tokens/s
63
ms