TEST #1335 RESULTS
08/07/2025 - 8:37 AM
ACCELERATOR
MODEL
59.1
tokens/s
generation
989
ms
time to first token
1304
tokens/s
prompt
427
LocalScore
HOW YOU STACK UP
Explore All Resultsgemma-2b-it - Q4_0
SYSTEM
CPU
Intel Core i5-6600K CPU @ 3.50GHz (skylake)
RAM
15.1GB
OS
Linux
Kernel Release
6.14.0-27-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #27-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:01:58 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1466
tokens/s
64.5
tokens/s
714
ms
pp4096+tg256
1284
tokens/s
45.0
tokens/s
3.21
sec
pp2048+tg256
1403
tokens/s
58.8
tokens/s
1.48
sec
pp2048+tg768
1400
tokens/s
57.6
tokens/s
1.48
sec
pp1024+tg1024
1456
tokens/s
60.9
tokens/s
719
ms
pp1280+tg3072
1420
tokens/s
52.0
tokens/s
917
ms
pp384+tg1152
1463
tokens/s
63.4
tokens/s
278
ms
pp64+tg1024
1219
tokens/s
65.3
tokens/s
67
ms
pp16+tg1536
624
tokens/s
64.2
tokens/s
40
ms