TEST #2791 RESULTS
02/23/2026 - 3:34 AM
ACCELERATOR
MODEL
106
tokens/s
generation
235
ms
time to first token
6629
tokens/s
prompt
1439
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepBrainz R1 0.6B v2 - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
8931
tokens/s
115
tokens/s
123
ms
pp4096+tg256
4420
tokens/s
97.9
tokens/s
937
ms
pp2048+tg256
6424
tokens/s
113
tokens/s
328
ms
pp2048+tg768
6345
tokens/s
111
tokens/s
332
ms
pp1024+tg1024
8284
tokens/s
113
tokens/s
133
ms
pp1280+tg3072
7864
tokens/s
104
tokens/s
173
ms
pp384+tg1152
11881
tokens/s
99.6
tokens/s
43
ms
pp64+tg1024
4141
tokens/s
99.6
tokens/s
26
ms
pp16+tg1536
1367
tokens/s
101
tokens/s
22
ms