TEST #2319 RESULTS
01/16/2026 - 10:17 PM
ACCELERATOR
MODEL
361
tokens/s
generation
90
ms
time to first token
14974
tokens/s
prompt
3919
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14400 (alderlake)
RAM
125.6GB
OS
Linux
Kernel Release
6.14.0-37-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #37~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 20 10:25:38 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
17880
tokens/s
374
tokens/s
60
ms
pp4096+tg256
12774
tokens/s
305
tokens/s
324
ms
pp2048+tg256
16585
tokens/s
352
tokens/s
126
ms
pp2048+tg768
16524
tokens/s
344
tokens/s
127
ms
pp1024+tg1024
19349
tokens/s
364
tokens/s
56
ms
pp1280+tg3072
18050
tokens/s
337
tokens/s
74
ms
pp384+tg1152
21019
tokens/s
381
tokens/s
21
ms
pp64+tg1024
10902
tokens/s
398
tokens/s
8
ms
pp16+tg1536
1684
tokens/s
390
tokens/s
12
ms