TEST #2787 RESULTS
02/22/2026 - 10:44 PM
ACCELERATOR
MODEL
34.2
tokens/s
generation
3.39
sec
time to first token
367
tokens/s
prompt
155
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
64GB
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 20:48:41 PST 2026; root:xnu-12377.81.4~5/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
419
tokens/s
37.3
tokens/s
2.47
sec
pp4096+tg256
383
tokens/s
26.1
tokens/s
10.73
sec
pp2048+tg256
407
tokens/s
32.4
tokens/s
5.06
sec
pp2048+tg768
407
tokens/s
31.4
tokens/s
5.06
sec
pp1024+tg1024
417
tokens/s
35.0
tokens/s
2.48
sec
pp1280+tg3072
392
tokens/s
30.0
tokens/s
3.29
sec
pp384+tg1152
384
tokens/s
37.5
tokens/s
1.03
sec
pp64+tg1024
353
tokens/s
39.4
tokens/s
205
ms
pp16+tg1536
141
tokens/s
38.5
tokens/s
137
ms