TEST #3319 RESULTS
04/15/2026 - 10:41 PM
ACCELERATOR
MODEL
342
tokens/s
generation
98
ms
time to first token
13768
tokens/s
prompt
3642
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
17204
tokens/s
346
tokens/s
62
ms
pp4096+tg256
11988
tokens/s
291
tokens/s
345
ms
pp2048+tg256
14891
tokens/s
337
tokens/s
141
ms
pp2048+tg768
15317
tokens/s
331
tokens/s
137
ms
pp1024+tg1024
18012
tokens/s
348
tokens/s
60
ms
pp1280+tg3072
16769
tokens/s
319
tokens/s
79
ms
pp384+tg1152
17931
tokens/s
362
tokens/s
24
ms
pp64+tg1024
10968
tokens/s
379
tokens/s
8
ms
pp16+tg1536
834
tokens/s
369
tokens/s
22
ms