TEST #30 RESULTS
03/28/2025 - 12:15 AM
ACCELERATOR
MODEL
117
tokens/s
generation
438
ms
time to first token
3003
tokens/s
prompt
928
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
3714
tokens/s
119
tokens/s
284
ms
pp4096+tg256
2677
tokens/s
83.6
tokens/s
1.54
sec
pp2048+tg256
3271
tokens/s
110
tokens/s
635
ms
pp2048+tg768
3261
tokens/s
104
tokens/s
637
ms
pp1024+tg1024
3618
tokens/s
120
tokens/s
291
ms
pp1280+tg3072
3410
tokens/s
98.7
tokens/s
384
ms
pp384+tg1152
3669
tokens/s
134
tokens/s
111
ms
pp64+tg1024
2590
tokens/s
144
tokens/s
31
ms
pp16+tg1536
820
tokens/s
136
tokens/s
26
ms