TEST #49 RESULTS
03/28/2025 - 8:41 PM
ACCELERATOR
MODEL
283
tokens/s
generation
113
ms
time to first token
12108
tokens/s
prompt
3117
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon Gold 6342 CPU @ 2.80GHz (icelake-server)
RAM
503.5GB
OS
Linux
Kernel Release
6.8.0-48-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #48~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Oct 7 11:24:13 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
15753
tokens/s
294
tokens/s
68
ms
pp4096+tg256
9844
tokens/s
243
tokens/s
420
ms
pp2048+tg256
13208
tokens/s
277
tokens/s
159
ms
pp2048+tg768
13224
tokens/s
273
tokens/s
158
ms
pp1024+tg1024
15749
tokens/s
288
tokens/s
68
ms
pp1280+tg3072
14689
tokens/s
265
tokens/s
91
ms
pp384+tg1152
16994
tokens/s
296
tokens/s
26
ms
pp64+tg1024
8362
tokens/s
308
tokens/s
11
ms
pp16+tg1536
1154
tokens/s
302
tokens/s
17
ms