TEST #3016 RESULTS
03/07/2026 - 10:14 PM
ACCELERATOR
MODEL
96.1
tokens/s
generation
329
ms
time to first token
4565
tokens/s
prompt
1101
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
5942
tokens/s
118
tokens/s
181
ms
pp4096+tg256
3199
tokens/s
23.3
tokens/s
1.32
sec
pp2048+tg256
4543
tokens/s
86.3
tokens/s
462
ms
pp2048+tg768
4546
tokens/s
81.2
tokens/s
462
ms
pp1024+tg1024
5826
tokens/s
102
tokens/s
184
ms
pp1280+tg3072
5491
tokens/s
62.5
tokens/s
242
ms
pp384+tg1152
6694
tokens/s
122
tokens/s
64
ms
pp64+tg1024
3184
tokens/s
139
tokens/s
26
ms
pp16+tg1536
1654
tokens/s
129
tokens/s
15
ms