TEST #839 RESULTS
05/07/2025 - 6:51 PM
ACCELERATOR
MODEL
171
tokens/s
generation
177
ms
time to first token
8699
tokens/s
prompt
2033
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700F @ 2.50GHz (rocketlake)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
11042
tokens/s
174
tokens/s
99
ms
pp4096+tg256
5925
tokens/s
156
tokens/s
700
ms
pp2048+tg256
8509
tokens/s
167
tokens/s
247
ms
pp2048+tg768
8523
tokens/s
169
tokens/s
246
ms
pp1024+tg1024
10957
tokens/s
173
tokens/s
102
ms
pp1280+tg3072
10334
tokens/s
169
tokens/s
134
ms
pp384+tg1152
14711
tokens/s
174
tokens/s
32
ms
pp64+tg1024
6413
tokens/s
177
tokens/s
16
ms
pp16+tg1536
1873
tokens/s
178
tokens/s
15
ms