TEST #97 RESULTS
03/28/2025 - 9:33 PM
ACCELERATOR
MODEL
116
tokens/s
generation
438
ms
time to first token
2993
tokens/s
prompt
926
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
3699
tokens/s
121
tokens/s
285
ms
pp4096+tg256
2679
tokens/s
82.6
tokens/s
1.54
sec
pp2048+tg256
3267
tokens/s
109
tokens/s
636
ms
pp2048+tg768
3254
tokens/s
105
tokens/s
639
ms
pp1024+tg1024
3635
tokens/s
122
tokens/s
289
ms
pp1280+tg3072
3401
tokens/s
98.8
tokens/s
385
ms
pp384+tg1152
3624
tokens/s
132
tokens/s
113
ms
pp64+tg1024
2537
tokens/s
141
tokens/s
32
ms
pp16+tg1536
838
tokens/s
137
tokens/s
25
ms