TEST #4106 RESULTS
08/31/2026 - 7:39 PM
ACCELERATOR
MODEL
137
tokens/s
generation
392
ms
time to first token
3705
tokens/s
prompt
1090
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
38.9GB
OS
Linux
Kernel Release
7.1.8-1-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue, 11 Aug 2026 14:27:10 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4341
tokens/s
149
tokens/s
243
ms
pp4096+tg256
2807
tokens/s
112
tokens/s
1.47
sec
pp2048+tg256
3682
tokens/s
132
tokens/s
564
ms
pp2048+tg768
3675
tokens/s
129
tokens/s
565
ms
pp1024+tg1024
4364
tokens/s
140
tokens/s
241
ms
pp1280+tg3072
4101
tokens/s
123
tokens/s
319
ms
pp384+tg1152
5004
tokens/s
146
tokens/s
83
ms
pp64+tg1024
4349
tokens/s
152
tokens/s
21
ms
pp16+tg1536
1026
tokens/s
149
tokens/s
22
ms