TEST #2274 RESULTS
01/13/2026 - 3:13 AM
ACCELERATOR
MODEL
189
tokens/s
generation
179
ms
time to first token
8786
tokens/s
prompt
2101
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon W-2133 CPU @ 3.60GHz (skylake-avx512)
RAM
94.3GB
OS
Linux
Kernel Release
6.8.0-90-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #91-Ubuntu SMP PREEMPT_DYNAMIC Tue Nov 18 14:14:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10776
tokens/s
190
tokens/s
100
ms
pp4096+tg256
5821
tokens/s
167
tokens/s
710
ms
pp2048+tg256
8347
tokens/s
187
tokens/s
251
ms
pp2048+tg768
8345
tokens/s
185
tokens/s
251
ms
pp1024+tg1024
11000
tokens/s
194
tokens/s
98
ms
pp1280+tg3072
10117
tokens/s
179
tokens/s
132
ms
pp384+tg1152
16005
tokens/s
199
tokens/s
29
ms
pp64+tg1024
8014
tokens/s
203
tokens/s
13
ms
pp16+tg1536
645
tokens/s
200
tokens/s
29
ms