TEST #2315 RESULTS
01/16/2026 - 8:24 PM
ACCELERATOR
MODEL
25.0
tokens/s
generation
4.08
sec
time to first token
308
tokens/s
prompt
124
LocalScore
HOW YOU STACK UP
Explore All ResultsGlm 4 9b Chat - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Wed Nov 5 21:30:44 PST 2025; root:xnu-11417.140.69.705.2~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
349
tokens/s
27.3
tokens/s
2.97
sec
pp4096+tg256
315
tokens/s
19.1
tokens/s
13.05
sec
pp2048+tg256
338
tokens/s
23.8
tokens/s
6.11
sec
pp2048+tg768
335
tokens/s
23.0
tokens/s
6.15
sec
pp1024+tg1024
347
tokens/s
25.5
tokens/s
2.99
sec
pp1280+tg3072
330
tokens/s
21.8
tokens/s
3.92
sec
pp384+tg1152
343
tokens/s
27.5
tokens/s
1.15
sec
pp64+tg1024
300
tokens/s
28.7
tokens/s
245
ms
pp16+tg1536
119
tokens/s
27.9
tokens/s
167
ms