TEST #920 RESULTS
05/19/2025 - 3:16 PM
ACCELERATOR
MODEL
249
tokens/s
generation
129
ms
time to first token
9892
tokens/s
prompt
2672
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6152 CPU @ 2.10GHz (skylake-avx512)
RAM
503.5GB
OS
Linux
Kernel Release
5.15.0-101-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #111-Ubuntu SMP Tue Mar 5 20:16:58 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12952
tokens/s
268
tokens/s
83
ms
pp4096+tg256
9129
tokens/s
189
tokens/s
454
ms
pp2048+tg256
11396
tokens/s
234
tokens/s
184
ms
pp2048+tg768
11412
tokens/s
228
tokens/s
184
ms
pp1024+tg1024
12932
tokens/s
258
tokens/s
83
ms
pp1280+tg3072
11911
tokens/s
219
tokens/s
112
ms
pp384+tg1152
12681
tokens/s
277
tokens/s
34
ms
pp64+tg1024
4066
tokens/s
287
tokens/s
19
ms
pp16+tg1536
2551
tokens/s
281
tokens/s
10
ms