TEST #154 RESULTS
03/28/2025 - 10:54 PM
ACCELERATOR
MODEL
273
tokens/s
generation
117
ms
time to first token
11451
tokens/s
prompt
2992
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q6_K
SYSTEM
CPU
AMD EPYC 7302 16-Core Processor (znver2)
RAM
251.6GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
14326
tokens/s
282
tokens/s
75
ms
pp4096+tg256
9967
tokens/s
238
tokens/s
415
ms
pp2048+tg256
12677
tokens/s
268
tokens/s
165
ms
pp2048+tg768
12638
tokens/s
264
tokens/s
166
ms
pp1024+tg1024
14871
tokens/s
279
tokens/s
72
ms
pp1280+tg3072
13611
tokens/s
257
tokens/s
98
ms
pp384+tg1152
15387
tokens/s
286
tokens/s
28
ms
pp64+tg1024
8482
tokens/s
292
tokens/s
11
ms
pp16+tg1536
1100
tokens/s
288
tokens/s
18
ms