TEST #2221 RESULTS
01/10/2026 - 11:41 AM
ACCELERATOR
MODEL
222
tokens/s
generation
199
ms
time to first token
6743
tokens/s
prompt
1960
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
30.9GB
OS
Linux
Kernel Release
6.14.0-37-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #37~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 20 10:25:38 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8442
tokens/s
241
tokens/s
125
ms
pp4096+tg256
5697
tokens/s
173
tokens/s
725
ms
pp2048+tg256
7346
tokens/s
210
tokens/s
284
ms
pp2048+tg768
7364
tokens/s
203
tokens/s
283
ms
pp1024+tg1024
8492
tokens/s
225
tokens/s
125
ms
pp1280+tg3072
7987
tokens/s
194
tokens/s
165
ms
pp384+tg1152
8248
tokens/s
243
tokens/s
50
ms
pp64+tg1024
6001
tokens/s
258
tokens/s
14
ms
pp16+tg1536
1110
tokens/s
249
tokens/s
18
ms