TEST #3366 RESULTS
04/23/2026 - 3:37 AM
ACCELERATOR
MODEL
288
tokens/s
generation
132
ms
time to first token
10515
tokens/s
prompt
2845
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14500 (alderlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.12.73+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.73-1 (2026-02-17)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12606
tokens/s
301
tokens/s
85
ms
pp4096+tg256
8588
tokens/s
247
tokens/s
481
ms
pp2048+tg256
11042
tokens/s
283
tokens/s
189
ms
pp2048+tg768
11046
tokens/s
277
tokens/s
189
ms
pp1024+tg1024
12859
tokens/s
295
tokens/s
83
ms
pp1280+tg3072
12232
tokens/s
268
tokens/s
108
ms
pp384+tg1152
15073
tokens/s
304
tokens/s
29
ms
pp64+tg1024
9355
tokens/s
311
tokens/s
10
ms
pp16+tg1536
1835
tokens/s
306
tokens/s
12
ms