TEST #1740 RESULTS
11/05/2025 - 5:15 PM
ACCELERATOR
MODEL
94.3
tokens/s
generation
597
ms
time to first token
2191
tokens/s
prompt
702
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6138 CPU @ 2.00GHz (skylake-avx512)
RAM
125.6GB
OS
Linux
Kernel Release
6.14.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Oct 14 13:55:17 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2600
tokens/s
99.1
tokens/s
405
ms
pp4096+tg256
2015
tokens/s
64.4
tokens/s
2.05
sec
pp2048+tg256
2367
tokens/s
86.6
tokens/s
877
ms
pp2048+tg768
2360
tokens/s
83.8
tokens/s
879
ms
pp1024+tg1024
2585
tokens/s
98.8
tokens/s
406
ms
pp1280+tg3072
2445
tokens/s
78.8
tokens/s
533
ms
pp384+tg1152
2672
tokens/s
108
tokens/s
152
ms
pp64+tg1024
1886
tokens/s
117
tokens/s
41
ms
pp16+tg1536
790
tokens/s
112
tokens/s
27
ms