TEST #44 RESULTS
03/28/2025 - 6:56 PM
ACCELERATOR
MODEL
241
tokens/s
generation
168
ms
time to first token
8404
tokens/s
prompt
2296
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7702 64-Core Processor (znver2)
RAM
503.5GB
OS
Linux
Kernel Release
6.8.0-40-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10403
tokens/s
253
tokens/s
102
ms
pp4096+tg256
6632
tokens/s
209
tokens/s
622
ms
pp2048+tg256
8725
tokens/s
237
tokens/s
239
ms
pp2048+tg768
8730
tokens/s
232
tokens/s
239
ms
pp1024+tg1024
10384
tokens/s
246
tokens/s
103
ms
pp1280+tg3072
9736
tokens/s
226
tokens/s
136
ms
pp384+tg1152
12622
tokens/s
254
tokens/s
34
ms
pp64+tg1024
7529
tokens/s
261
tokens/s
12
ms
pp16+tg1536
880
tokens/s
256
tokens/s
22
ms