TEST #2726 RESULTS
02/17/2026 - 11:59 PM
ACCELERATOR
MODEL
279
tokens/s
generation
116
ms
time to first token
13888
tokens/s
prompt
3219
LocalScore
HOW YOU STACK UP
Explore All Resultsllama - IQ4_XS - 4.25 bpw
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
19911
tokens/s
357
tokens/s
54
ms
pp4096+tg256
18318
tokens/s
319
tokens/s
229
ms
pp2048+tg256
51812
tokens/s
316
tokens/s
42
ms
pp2048+tg768
11558
tokens/s
320
tokens/s
179
ms
pp1024+tg1024
8103
tokens/s
283
tokens/s
130
ms
pp1280+tg3072
7022
tokens/s
228
tokens/s
187
ms
pp384+tg1152
7336
tokens/s
256
tokens/s
63
ms
pp64+tg1024
642
tokens/s
221
tokens/s
103
ms
pp16+tg1536
290
tokens/s
212
tokens/s
59
ms