TEST #1644 RESULTS
10/13/2025 - 11:48 AM
ACCELERATOR
MODEL
406
tokens/s
generation
54
ms
time to first token
26670
tokens/s
prompt
5867
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 75F3 32-Core Processor (znver3)
RAM
503.7GB
OS
Linux
Kernel Release
6.8.0-63-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #66-Ubuntu SMP PREEMPT_DYNAMIC Fri Jun 13 20:25:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
37601
tokens/s
402
tokens/s
30
ms
pp4096+tg256
19637
tokens/s
362
tokens/s
211
ms
pp2048+tg256
28871
tokens/s
386
tokens/s
74
ms
pp2048+tg768
29024
tokens/s
390
tokens/s
73
ms
pp1024+tg1024
38243
tokens/s
411
tokens/s
29
ms
pp1280+tg3072
36685
tokens/s
385
tokens/s
37
ms
pp384+tg1152
34184
tokens/s
430
tokens/s
13
ms
pp64+tg1024
11848
tokens/s
447
tokens/s
8
ms
pp16+tg1536
3940
tokens/s
437
tokens/s
6
ms