TEST #1026 RESULTS

06/10/2025 - 4:38 AM

23.0

tokens/s

generation

4.45

sec

time to first token

276

tokens/s

prompt

113

LocalScore

HOW YOU STACK UP
Explore All Results

Granite 3.3 8b Instruct - Q5_K - Medium

SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
64GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
331
tokens/s
25.3
tokens/s
3.13
sec
pp4096+tg256
302
tokens/s
18.5
tokens/s
13.64
sec
pp2048+tg256
317
tokens/s
22.3
tokens/s
6.50
sec
pp2048+tg768
295
tokens/s
21.7
tokens/s
6.99
sec
pp1024+tg1024
291
tokens/s
23.5
tokens/s
3.57
sec
pp1280+tg3072
292
tokens/s
20.9
tokens/s
4.42
sec
pp384+tg1152
307
tokens/s
25.5
tokens/s
1.29
sec
pp64+tg1024
247
tokens/s
25.2
tokens/s
294
ms
pp16+tg1536
105
tokens/s
24.5
tokens/s
190
ms