TEST #1221 RESULTS
07/15/2025 - 8:43 AM
ACCELERATOR
MODEL
197
tokens/s
generation
232
ms
time to first token
6058
tokens/s
prompt
1727
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-7700T CPU @ 2.90GHz (skylake)
RAM
27.4GB
OS
Linux
Kernel Release
6.12.30+bpo-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.30-1~bpo12+1 (2025-06-14)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7305
tokens/s
215
tokens/s
145
ms
pp4096+tg256
4770
tokens/s
157
tokens/s
865
ms
pp2048+tg256
6285
tokens/s
189
tokens/s
331
ms
pp2048+tg768
6233
tokens/s
185
tokens/s
334
ms
pp1024+tg1024
7292
tokens/s
201
tokens/s
145
ms
pp1280+tg3072
7081
tokens/s
178
tokens/s
186
ms
pp384+tg1152
8288
tokens/s
212
tokens/s
51
ms
pp64+tg1024
6084
tokens/s
223
tokens/s
15
ms
pp16+tg1536
1185
tokens/s
217
tokens/s
18
ms