TEST #989 RESULTS
06/04/2025 - 4:54 AM
ACCELERATOR
MODEL
319
tokens/s
generation
99
ms
time to first token
13125
tokens/s
prompt
3482
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2697A v4 @ 2.60GHz (broadwell)
RAM
125.7GB
OS
Linux
Kernel Release
6.1.0-34-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.1.135-1 (2025-04-25)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
16839
tokens/s
328
tokens/s
64
ms
pp4096+tg256
11820
tokens/s
278
tokens/s
350
ms
pp2048+tg256
14975
tokens/s
318
tokens/s
140
ms
pp2048+tg768
15148
tokens/s
311
tokens/s
138
ms
pp1024+tg1024
17472
tokens/s
328
tokens/s
62
ms
pp1280+tg3072
16284
tokens/s
299
tokens/s
82
ms
pp384+tg1152
17505
tokens/s
329
tokens/s
25
ms
pp64+tg1024
7033
tokens/s
336
tokens/s
13
ms
pp16+tg1536
1051
tokens/s
343
tokens/s
18
ms