TEST #111 RESULTS
03/28/2025 - 9:50 PM
ACCELERATOR
MODEL
195
tokens/s
generation
287
ms
time to first token
5553
tokens/s
prompt
1558
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2687W 0 @ 3.10GHz (sandybridge)
RAM
503.8GB
OS
Linux
Kernel Release
6.8.0-52-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #53~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jan 15 19:18:46 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6972
tokens/s
214
tokens/s
152
ms
pp4096+tg256
4921
tokens/s
149
tokens/s
839
ms
pp2048+tg256
6155
tokens/s
184
tokens/s
338
ms
pp2048+tg768
6115
tokens/s
179
tokens/s
340
ms
pp1024+tg1024
6940
tokens/s
201
tokens/s
152
ms
pp1280+tg3072
6600
tokens/s
170
tokens/s
199
ms
pp384+tg1152
7220
tokens/s
213
tokens/s
58
ms
pp64+tg1024
5025
tokens/s
225
tokens/s
17
ms
pp16+tg1536
33
tokens/s
219
tokens/s
484
ms