TEST #100 RESULTS
03/28/2025 - 9:35 PM
ACCELERATOR
MODEL
124
tokens/s
generation
477
ms
time to first token
2516
tokens/s
prompt
868
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
376.5GB
OS
Linux
Kernel Release
6.8.0-45-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #45~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Sep 11 15:25:05 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3118
tokens/s
137
tokens/s
336
ms
pp4096+tg256
2655
tokens/s
88.2
tokens/s
1.55
sec
pp2048+tg256
2944
tokens/s
115
tokens/s
704
ms
pp2048+tg768
2946
tokens/s
111
tokens/s
704
ms
pp1024+tg1024
3121
tokens/s
127
tokens/s
335
ms
pp1280+tg3072
2985
tokens/s
105
tokens/s
437
ms
pp384+tg1152
3016
tokens/s
140
tokens/s
134
ms
pp64+tg1024
1417
tokens/s
150
tokens/s
51
ms
pp16+tg1536
441
tokens/s
144
tokens/s
42
ms