TEST #174 RESULTS
03/30/2025 - 8:13 PM
ACCELERATOR
MODEL
238
tokens/s
generation
94
ms
time to first token
16125
tokens/s
prompt
3439
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
21380
tokens/s
274
tokens/s
52
ms
pp4096+tg256
12023
tokens/s
154
tokens/s
347
ms
pp2048+tg256
17085
tokens/s
215
tokens/s
124
ms
pp2048+tg768
17017
tokens/s
203
tokens/s
125
ms
pp1024+tg1024
21359
tokens/s
242
tokens/s
52
ms
pp1280+tg3072
19518
tokens/s
190
tokens/s
70
ms
pp384+tg1152
25543
tokens/s
274
tokens/s
18
ms
pp64+tg1024
10866
tokens/s
301
tokens/s
9
ms
pp16+tg1536
331
tokens/s
287
tokens/s
51
ms