TEST #2198 RESULTS
01/08/2026 - 3:39 PM
ACCELERATOR
MODEL
58.9
tokens/s
generation
672
ms
time to first token
1881
tokens/s
prompt
548
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-9900K CPU @ 3.60GHz (skylake)
RAM
15.5GB
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
2413
tokens/s
62.0
tokens/s
441
ms
pp4096+tg256
2007
tokens/s
53.0
tokens/s
2.06
sec
pp2048+tg256
2271
tokens/s
58.3
tokens/s
919
ms
pp2048+tg768
2278
tokens/s
57.6
tokens/s
916
ms
pp1024+tg1024
2381
tokens/s
59.8
tokens/s
446
ms
pp1280+tg3072
2342
tokens/s
56.0
tokens/s
563
ms
pp384+tg1152
2373
tokens/s
60.2
tokens/s
427
ms
pp64+tg1024
766
tokens/s
62.0
tokens/s
99
ms
pp16+tg1536
98
tokens/s
61.3
tokens/s
180
ms