TEST #2291 RESULTS
01/15/2026 - 4:03 AM
ACCELERATOR
MODEL
360
tokens/s
generation
89
ms
time to first token
15064
tokens/s
prompt
3934
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14400 (alderlake)
RAM
125.6GB
OS
Linux
Kernel Release
6.14.0-37-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #37~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 20 10:25:38 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
19447
tokens/s
375
tokens/s
55
ms
pp4096+tg256
12822
tokens/s
306
tokens/s
323
ms
pp2048+tg256
16618
tokens/s
352
tokens/s
126
ms
pp2048+tg768
16586
tokens/s
345
tokens/s
126
ms
pp1024+tg1024
19363
tokens/s
365
tokens/s
56
ms
pp1280+tg3072
18015
tokens/s
335
tokens/s
74
ms
pp384+tg1152
20116
tokens/s
378
tokens/s
22
ms
pp64+tg1024
10929
tokens/s
396
tokens/s
8
ms
pp16+tg1536
1674
tokens/s
388
tokens/s
12
ms