TEST #3028 RESULTS
03/07/2026 - 10:31 PM
ACCELERATOR
MODEL
210
tokens/s
generation
223
ms
time to first token
6386
tokens/s
prompt
1819
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
RAM
62.6GB
OS
Linux
Kernel Release
6.18.13-arch1-1.1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 26 Feb 2026 22:40:21 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7723
tokens/s
226
tokens/s
137
ms
pp4096+tg256
4976
tokens/s
169
tokens/s
829
ms
pp2048+tg256
6473
tokens/s
202
tokens/s
321
ms
pp2048+tg768
6483
tokens/s
197
tokens/s
321
ms
pp1024+tg1024
7626
tokens/s
214
tokens/s
139
ms
pp1280+tg3072
7194
tokens/s
190
tokens/s
182
ms
pp384+tg1152
8936
tokens/s
226
tokens/s
47
ms
pp64+tg1024
6578
tokens/s
235
tokens/s
14
ms
pp16+tg1536
1490
tokens/s
231
tokens/s
15
ms