TEST #3648 RESULTS
05/29/2026 - 11:30 AM
ACCELERATOR
MODEL
51.5
tokens/s
generation
1.05
sec
time to first token
1216
tokens/s
prompt
391
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900K (alderlake)
RAM
62.1GB
OS
Linux
Kernel Release
6.12.90+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.90-1 (2026-05-22)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1445
tokens/s
56.6
tokens/s
727
ms
pp4096+tg256
1216
tokens/s
43.8
tokens/s
3.39
sec
pp2048+tg256
1301
tokens/s
48.4
tokens/s
1.59
sec
pp2048+tg768
1291
tokens/s
48.8
tokens/s
1.61
sec
pp1024+tg1024
1395
tokens/s
52.8
tokens/s
751
ms
pp1280+tg3072
1376
tokens/s
47.0
tokens/s
947
ms
pp384+tg1152
1427
tokens/s
54.2
tokens/s
286
ms
pp64+tg1024
1166
tokens/s
56.5
tokens/s
70
ms
pp16+tg1536
324
tokens/s
55.1
tokens/s
66
ms