TEST #127 RESULTS
03/28/2025 - 10:08 PM
ACCELERATOR
MODEL
346
tokens/s
generation
87
ms
time to first token
15175
tokens/s
prompt
3928
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2699 v3 @ 2.30GHz (haswell)
RAM
125.8GB
OS
Linux
Kernel Release
5.15.0-134-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #145-Ubuntu SMP Wed Feb 12 20:08:39 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
19236
tokens/s
361
tokens/s
56
ms
pp4096+tg256
13474
tokens/s
296
tokens/s
307
ms
pp2048+tg256
17269
tokens/s
341
tokens/s
122
ms
pp2048+tg768
17302
tokens/s
333
tokens/s
121
ms
pp1024+tg1024
19724
tokens/s
351
tokens/s
55
ms
pp1280+tg3072
18604
tokens/s
323
tokens/s
72
ms
pp384+tg1152
20212
tokens/s
362
tokens/s
22
ms
pp64+tg1024
9578
tokens/s
376
tokens/s
9
ms
pp16+tg1536
1173
tokens/s
369
tokens/s
16
ms