TEST #138 RESULTS
03/28/2025 - 10:17 PM
ACCELERATOR
MODEL
309
tokens/s
generation
99
ms
time to first token
15156
tokens/s
prompt
3615
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7542 32-Core Processor (znver2)
RAM
125.7GB
OS
Linux
Kernel Release
5.15.0-92-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #102-Ubuntu SMP Wed Jan 10 09:33:48 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
19365
tokens/s
316
tokens/s
56
ms
pp4096+tg256
10583
tokens/s
274
tokens/s
391
ms
pp2048+tg256
15447
tokens/s
304
tokens/s
136
ms
pp2048+tg768
15421
tokens/s
301
tokens/s
136
ms
pp1024+tg1024
20250
tokens/s
316
tokens/s
54
ms
pp1280+tg3072
19256
tokens/s
293
tokens/s
70
ms
pp384+tg1152
24887
tokens/s
322
tokens/s
19
ms
pp64+tg1024
10347
tokens/s
328
tokens/s
9
ms
pp16+tg1536
850
tokens/s
326
tokens/s
22
ms