TEST #25 RESULTS
03/27/2025 - 10:54 PM
ACCELERATOR
MODEL
114
tokens/s
generation
445
ms
time to first token
2944
tokens/s
prompt
911
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2680 v2 @ 2.80GHz (ivybridge)
RAM
251.6GB
OS
Linux
Kernel Release
6.8.0-51-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #52~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Dec 9 15:00:52 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3659
tokens/s
121
tokens/s
288
ms
pp4096+tg256
2641
tokens/s
82.2
tokens/s
1.56
sec
pp2048+tg256
3219
tokens/s
107
tokens/s
646
ms
pp2048+tg768
3196
tokens/s
105
tokens/s
650
ms
pp1024+tg1024
3566
tokens/s
118
tokens/s
295
ms
pp1280+tg3072
3329
tokens/s
97.3
tokens/s
393
ms
pp384+tg1152
3527
tokens/s
131
tokens/s
116
ms
pp64+tg1024
2550
tokens/s
138
tokens/s
31
ms
pp16+tg1536
810
tokens/s
130
tokens/s
26
ms