TEST #1757 RESULTS
11/08/2025 - 2:05 AM
ACCELERATOR
MODEL
91.9
tokens/s
generation
423
ms
time to first token
6509
tokens/s
prompt
1122
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7700X 8-Core Processor (znver4)
RAM
61.9GB
OS
Linux
Kernel Release
6.14.0-35-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #35~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Oct 14 13:55:17 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8753
tokens/s
111
tokens/s
126
ms
pp4096+tg256
5416
tokens/s
57.2
tokens/s
774
ms
pp2048+tg256
7288
tokens/s
86.0
tokens/s
293
ms
pp2048+tg768
7241
tokens/s
80.6
tokens/s
295
ms
pp1024+tg1024
8749
tokens/s
97.1
tokens/s
127
ms
pp1280+tg3072
7794
tokens/s
70.9
tokens/s
175
ms
pp384+tg1152
9729
tokens/s
104
tokens/s
49
ms
pp64+tg1024
3604
tokens/s
112
tokens/s
26
ms
pp16+tg1536
8
tokens/s
108
tokens/s
1.95
sec