TEST #161 RESULTS
03/29/2025 - 4:20 AM
ACCELERATOR
MODEL
240
tokens/s
generation
92
ms
time to first token
16482
tokens/s
prompt
3506
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14600KF (alderlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
21970
tokens/s
276
tokens/s
50
ms
pp4096+tg256
12222
tokens/s
155
tokens/s
341
ms
pp2048+tg256
17297
tokens/s
218
tokens/s
123
ms
pp2048+tg768
17208
tokens/s
205
tokens/s
124
ms
pp1024+tg1024
22022
tokens/s
244
tokens/s
50
ms
pp1280+tg3072
20158
tokens/s
192
tokens/s
67
ms
pp384+tg1152
25731
tokens/s
277
tokens/s
18
ms
pp64+tg1024
11347
tokens/s
306
tokens/s
9
ms
pp16+tg1536
382
tokens/s
289
tokens/s
45
ms