TEST #3309 RESULTS
04/15/2026 - 3:43 AM
ACCELERATOR
MODEL
350
tokens/s
generation
93
ms
time to first token
14749
tokens/s
prompt
3811
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i9-12900K (alderlake)
RAM
91.8GB
OS
Linux
Kernel Release
6.8.0-107-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #107-Ubuntu SMP PREEMPT_DYNAMIC Fri Mar 13 19:51:50 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
18243
tokens/s
352
tokens/s
59
ms
pp4096+tg256
12198
tokens/s
300
tokens/s
339
ms
pp2048+tg256
15782
tokens/s
346
tokens/s
133
ms
pp2048+tg768
15741
tokens/s
338
tokens/s
133
ms
pp1024+tg1024
18300
tokens/s
357
tokens/s
59
ms
pp1280+tg3072
17086
tokens/s
326
tokens/s
78
ms
pp384+tg1152
20259
tokens/s
368
tokens/s
22
ms
pp64+tg1024
11549
tokens/s
385
tokens/s
8
ms
pp16+tg1536
3581
tokens/s
374
tokens/s
7
ms