TEST #461 RESULTS
04/07/2025 - 3:20 AM
ACCELERATOR
MODEL
328
tokens/s
generation
95
ms
time to first token
14169
tokens/s
prompt
3659
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-4670 CPU @ 3.40GHz (haswell)
RAM
15.5GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
18413
tokens/s
334
tokens/s
59
ms
pp4096+tg256
12020
tokens/s
278
tokens/s
345
ms
pp2048+tg256
15705
tokens/s
321
tokens/s
134
ms
pp2048+tg768
15700
tokens/s
315
tokens/s
134
ms
pp1024+tg1024
18218
tokens/s
335
tokens/s
59
ms
pp1280+tg3072
17046
tokens/s
305
tokens/s
78
ms
pp384+tg1152
19269
tokens/s
346
tokens/s
23
ms
pp64+tg1024
9718
tokens/s
363
tokens/s
9
ms
pp16+tg1536
1430
tokens/s
355
tokens/s
14
ms