TEST #3536 RESULTS
05/14/2026 - 3:59 PM
ACCELERATOR
MODEL
29.1
tokens/s
generation
3.61
sec
time to first token
340
tokens/s
prompt
140
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi-4-Mini-Reasoning - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
32GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:53:15 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
392
tokens/s
32.1
tokens/s
2.64
sec
pp4096+tg256
356
tokens/s
21.2
tokens/s
11.55
sec
pp2048+tg256
380
tokens/s
27.2
tokens/s
5.42
sec
pp2048+tg768
381
tokens/s
26.3
tokens/s
5.41
sec
pp1024+tg1024
390
tokens/s
29.8
tokens/s
2.66
sec
pp1280+tg3072
387
tokens/s
25.0
tokens/s
3.34
sec
pp384+tg1152
386
tokens/s
32.5
tokens/s
1.02
sec
pp64+tg1024
289
tokens/s
34.5
tokens/s
248
ms
pp16+tg1536
103
tokens/s
33.4
tokens/s
182
ms