TEST #3062 RESULTS
03/12/2026 - 12:23 AM
ACCELERATOR
MODEL
211
tokens/s
generation
222
ms
time to first token
6479
tokens/s
prompt
1833
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-14700 (alderlake)
RAM
93.9GB
OS
Linux
Kernel Release
6.12.73+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.73-1 (2026-02-17)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7794
tokens/s
228
tokens/s
136
ms
pp4096+tg256
4974
tokens/s
169
tokens/s
830
ms
pp2048+tg256
6507
tokens/s
203
tokens/s
320
ms
pp2048+tg768
6511
tokens/s
199
tokens/s
319
ms
pp1024+tg1024
7712
tokens/s
216
tokens/s
137
ms
pp1280+tg3072
7218
tokens/s
190
tokens/s
182
ms
pp384+tg1152
8791
tokens/s
227
tokens/s
48
ms
pp64+tg1024
6666
tokens/s
238
tokens/s
14
ms
pp16+tg1536
2140
tokens/s
232
tokens/s
14
ms