TEST #3051 RESULTS
03/09/2026 - 4:22 AM
ACCELERATOR
MODEL
46.7
tokens/s
generation
1.30
sec
time to first token
1053
tokens/s
prompt
335
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-7500 CPU @ 3.40GHz (skylake)
RAM
15.6GB
OS
Linux
Kernel Release
6.8.0-101-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #101-Ubuntu SMP PREEMPT_DYNAMIC Mon Feb 9 10:15:05 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1176
tokens/s
52.1
tokens/s
890
ms
pp4096+tg256
916
tokens/s
31.4
tokens/s
4.51
sec
pp2048+tg256
1078
tokens/s
42.7
tokens/s
1.92
sec
pp2048+tg768
1078
tokens/s
40.5
tokens/s
1.92
sec
pp1024+tg1024
1176
tokens/s
47.6
tokens/s
890
ms
pp1280+tg3072
1131
tokens/s
37.9
tokens/s
1.15
sec
pp384+tg1152
1242
tokens/s
53.6
tokens/s
327
ms
pp64+tg1024
1144
tokens/s
58.7
tokens/s
70
ms
pp16+tg1536
534
tokens/s
55.9
tokens/s
44
ms