TEST #485 RESULTS
04/07/2025 - 9:57 AM
ACCELERATOR
MODEL
24.4
tokens/s
generation
4.30
sec
time to first token
291
tokens/s
prompt
118
LocalScore
HOW YOU STACK UP
Explore All Resultsmeta-llama-7b - Q5_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:17:35 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
328
tokens/s
26.4
tokens/s
3.16
sec
pp4096+tg256
301
tokens/s
19.5
tokens/s
13.66
sec
pp2048+tg256
318
tokens/s
23.3
tokens/s
6.48
sec
pp2048+tg768
319
tokens/s
22.8
tokens/s
6.46
sec
pp1024+tg1024
327
tokens/s
24.9
tokens/s
3.17
sec
pp1280+tg3072
318
tokens/s
21.9
tokens/s
4.07
sec
pp384+tg1152
308
tokens/s
26.4
tokens/s
1.28
sec
pp64+tg1024
276
tokens/s
27.6
tokens/s
267
ms
pp16+tg1536
122
tokens/s
27.0
tokens/s
165
ms