TEST #2197 RESULTS
01/08/2026 - 2:54 PM
ACCELERATOR
MODEL
207
tokens/s
generation
148
ms
time to first token
11965
tokens/s
prompt
2559
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i9-13900HX (alderlake)
RAM
31.1GB
OS
Linux
Kernel Release
6.8.12-1-liquorix-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 ZEN SMP PREEMPT liquorix 6.8-18~mx23ahs (2024-05-31)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
13122
tokens/s
207
tokens/s
83
ms
pp4096+tg256
6799
tokens/s
179
tokens/s
610
ms
pp2048+tg256
10158
tokens/s
206
tokens/s
207
ms
pp2048+tg768
9542
tokens/s
197
tokens/s
221
ms
pp1024+tg1024
17647
tokens/s
215
tokens/s
62
ms
pp1280+tg3072
13735
tokens/s
197
tokens/s
98
ms
pp384+tg1152
24707
tokens/s
221
tokens/s
19
ms
pp64+tg1024
11129
tokens/s
228
tokens/s
9
ms
pp16+tg1536
850
tokens/s
218
tokens/s
22
ms