TEST #3478 RESULTS
05/09/2026 - 1:37 AM
ACCELERATOR
MODEL
189
tokens/s
generation
236
ms
time to first token
5696
tokens/s
prompt
1660
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-10870H CPU @ 2.20GHz (skylake)
RAM
62.6GB
OS
Linux
Kernel Release
6.17.0-23-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #23~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 14 16:11:48 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7127
tokens/s
208
tokens/s
148
ms
pp4096+tg256
4950
tokens/s
146
tokens/s
834
ms
pp2048+tg256
6212
tokens/s
178
tokens/s
335
ms
pp2048+tg768
6046
tokens/s
175
tokens/s
344
ms
pp1024+tg1024
7073
tokens/s
194
tokens/s
150
ms
pp1280+tg3072
6733
tokens/s
166
tokens/s
195
ms
pp384+tg1152
7503
tokens/s
206
tokens/s
56
ms
pp64+tg1024
5197
tokens/s
217
tokens/s
16
ms
pp16+tg1536
427
tokens/s
211
tokens/s
41
ms