TEST #1068 RESULTS
06/17/2025 - 7:36 PM
ACCELERATOR
MODEL
86.4
tokens/s
generation
322
ms
time to first token
3700
tokens/s
prompt
997
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700H (alderlake)
RAM
15.5GB
OS
Linux
Kernel Release
6.6.87.1-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Apr 21 17:08:54 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6758
tokens/s
154
tokens/s
158
ms
pp4096+tg256
4443
tokens/s
118
tokens/s
933
ms
pp2048+tg256
5232
tokens/s
127
tokens/s
400
ms
pp2048+tg768
4777
tokens/s
115
tokens/s
438
ms
pp1024+tg1024
4877
tokens/s
105
tokens/s
219
ms
pp1280+tg3072
4285
tokens/s
51.4
tokens/s
311
ms
pp384+tg1152
1489
tokens/s
35.0
tokens/s
286
ms
pp64+tg1024
1125
tokens/s
36.4
tokens/s
82
ms
pp16+tg1536
317
tokens/s
35.7
tokens/s
75
ms