TEST #1519 RESULTS
09/15/2025 - 10:55 AM
ACCELERATOR
MODEL
352
tokens/s
generation
82
ms
time to first token
17958
tokens/s
prompt
4266
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i9-13900KF (alderlake)
RAM
31.2GB
OS
Linux
Kernel Release
6.15.11-2-MANJARO
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat, 30 Aug 2025 05:31:45 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
23494
tokens/s
338
tokens/s
47
ms
pp4096+tg256
12536
tokens/s
334
tokens/s
330
ms
pp2048+tg256
20778
tokens/s
346
tokens/s
101
ms
pp2048+tg768
18378
tokens/s
339
tokens/s
115
ms
pp1024+tg1024
22642
tokens/s
372
tokens/s
49
ms
pp1280+tg3072
23210
tokens/s
334
tokens/s
58
ms
pp384+tg1152
25429
tokens/s
341
tokens/s
20
ms
pp64+tg1024
10770
tokens/s
397
tokens/s
9
ms
pp16+tg1536
4384
tokens/s
370
tokens/s
6
ms