TEST #775 RESULTS
04/26/2025 - 9:31 PM
ACCELERATOR
MODEL
250
tokens/s
generation
131
ms
time to first token
9743
tokens/s
prompt
2647
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 185H (alderlake)
RAM
93.8GB
OS
Linux
Kernel Release
6.14.3-2-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun, 20 Apr 2025 20:28:57 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
12912
tokens/s
289
tokens/s
83
ms
pp4096+tg256
9379
tokens/s
214
tokens/s
441
ms
pp2048+tg256
11738
tokens/s
262
tokens/s
178
ms
pp2048+tg768
11773
tokens/s
254
tokens/s
178
ms
pp1024+tg1024
13383
tokens/s
287
tokens/s
80
ms
pp1280+tg3072
12351
tokens/s
242
tokens/s
107
ms
pp384+tg1152
12271
tokens/s
264
tokens/s
35
ms
pp64+tg1024
3601
tokens/s
249
tokens/s
21
ms
pp16+tg1536
282
tokens/s
193
tokens/s
60
ms