TEST #1237 RESULTS
07/23/2025 - 8:59 AM
ACCELERATOR
MODEL
233
tokens/s
generation
172
ms
time to first token
8278
tokens/s
prompt
2238
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
62.8GB
OS
Linux
Kernel Release
6.15.7-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu, 17 Jul 2025 21:05:29 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10376
tokens/s
247
tokens/s
103
ms
pp4096+tg256
6595
tokens/s
202
tokens/s
626
ms
pp2048+tg256
8704
tokens/s
229
tokens/s
240
ms
pp2048+tg768
8666
tokens/s
225
tokens/s
241
ms
pp1024+tg1024
10330
tokens/s
234
tokens/s
103
ms
pp1280+tg3072
9728
tokens/s
215
tokens/s
136
ms
pp384+tg1152
12595
tokens/s
245
tokens/s
34
ms
pp64+tg1024
7162
tokens/s
250
tokens/s
13
ms
pp16+tg1536
345
tokens/s
247
tokens/s
50
ms