TEST #1424 RESULTS
08/24/2025 - 3:28 PM
ACCELERATOR
MODEL
43.6
tokens/s
generation
465
ms
time to first token
2759
tokens/s
prompt
637
LocalScore
HOW YOU STACK UP
Explore All Resultsgemma-3-12b-it-codeforces-SFT - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.16.1-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri, 15 Aug 2025 16:04:43 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3485
tokens/s
45.0
tokens/s
315
ms
pp4096+tg256
2712
tokens/s
38.9
tokens/s
1.53
sec
pp2048+tg256
3185
tokens/s
43.4
tokens/s
666
ms
pp2048+tg768
3148
tokens/s
42.9
tokens/s
674
ms
pp1024+tg1024
3502
tokens/s
43.9
tokens/s
316
ms
pp1280+tg3072
3097
tokens/s
41.1
tokens/s
438
ms
pp384+tg1152
3567
tokens/s
45.4
tokens/s
129
ms
pp64+tg1024
1561
tokens/s
46.5
tokens/s
62
ms
pp16+tg1536
571
tokens/s
45.2
tokens/s
49
ms