TEST #3185 RESULTS

03/25/2026 - 12:55 AM

33.8

tokens/s

generation

3.59

sec

time to first token

341

tokens/s

prompt

148

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M5 Max 6P+12E
RAM
36GB
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 20:54:38 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6050
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
394
tokens/s
36.6
tokens/s
2.63
sec
pp4096+tg256
360
tokens/s
29.0
tokens/s
11.42
sec
pp2048+tg256
383
tokens/s
33.5
tokens/s
5.37
sec
pp2048+tg768
383
tokens/s
32.8
tokens/s
5.38
sec
pp1024+tg1024
391
tokens/s
35.2
tokens/s
2.65
sec
pp1280+tg3072
388
tokens/s
31.4
tokens/s
3.33
sec
pp384+tg1152
356
tokens/s
34.9
tokens/s
1.11
sec
pp64+tg1024
301
tokens/s
35.8
tokens/s
238
ms
pp16+tg1536
111
tokens/s
35.1
tokens/s
169
ms