TEST #3187 RESULTS
03/25/2026 - 5:09 AM
ACCELERATOR
MODEL
192
tokens/s
generation
208
ms
time to first token
6950
tokens/s
prompt
1858
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-14900HX (alderlake)
RAM
31GB
OS
Linux
Kernel Release
6.18.7-76061807-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202601231045~1769703228~24.04~cb87b5b SMP PREEMPT_DYNAMIC Thu J
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8700
tokens/s
203
tokens/s
123
ms
pp4096+tg256
5121
tokens/s
160
tokens/s
806
ms
pp2048+tg256
7063
tokens/s
186
tokens/s
295
ms
pp2048+tg768
7058
tokens/s
183
tokens/s
296
ms
pp1024+tg1024
8781
tokens/s
196
tokens/s
122
ms
pp1280+tg3072
8264
tokens/s
177
tokens/s
160
ms
pp384+tg1152
12088
tokens/s
204
tokens/s
37
ms
pp64+tg1024
3629
tokens/s
212
tokens/s
22
ms
pp16+tg1536
1842
tokens/s
208
tokens/s
13
ms