TEST #4099 RESULTS
08/28/2026 - 7:37 PM
ACCELERATOR
MODEL
132
tokens/s
generation
1.15
sec
time to first token
1167
tokens/s
prompt
512
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Genuine Intel CPU 0000%@ (sapphirerapids)
RAM
125.5GB
OS
Linux
Kernel Release
6.12.105+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.105-1 (2026-08-24)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1423
tokens/s
136
tokens/s
729
ms
pp4096+tg256
980
tokens/s
140
tokens/s
4.19
sec
pp2048+tg256
1252
tokens/s
153
tokens/s
1.64
sec
pp2048+tg768
1240
tokens/s
151
tokens/s
1.66
sec
pp1024+tg1024
1400
tokens/s
75.9
tokens/s
741
ms
pp1280+tg3072
1356
tokens/s
84.9
tokens/s
953
ms
pp384+tg1152
1369
tokens/s
140
tokens/s
289
ms
pp64+tg1024
998
tokens/s
155
tokens/s
71
ms
pp16+tg1536
485
tokens/s
153
tokens/s
39
ms