TEST #2576 RESULTS
02/10/2026 - 9:06 AM
ACCELERATOR
MODEL
299
tokens/s
generation
155
ms
time to first token
10880
tokens/s
prompt
2759
LocalScore
HOW YOU STACK UP
Explore All ResultsLocutusqueXFelladrin TinyMistral248M Instruct - Q6_K
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
13629
tokens/s
330
tokens/s
78
ms
pp4096+tg256
6312
tokens/s
253
tokens/s
654
ms
pp2048+tg256
9801
tokens/s
294
tokens/s
213
ms
pp2048+tg768
9573
tokens/s
284
tokens/s
217
ms
pp1024+tg1024
13153
tokens/s
305
tokens/s
81
ms
pp1280+tg3072
12062
tokens/s
278
tokens/s
111
ms
pp384+tg1152
21812
tokens/s
312
tokens/s
21
ms
pp64+tg1024
9068
tokens/s
320
tokens/s
10
ms
pp16+tg1536
2510
tokens/s
318
tokens/s
9
ms