TEST #2964 RESULTS
03/04/2026 - 9:46 AM
ACCELERATOR
MODEL
30.5
tokens/s
generation
4.13
sec
time to first token
303
tokens/s
prompt
131
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
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
339
tokens/s
33.1
tokens/s
3.05
sec
pp4096+tg256
313
tokens/s
23.8
tokens/s
13.12
sec
pp2048+tg256
331
tokens/s
29.1
tokens/s
6.23
sec
pp2048+tg768
326
tokens/s
28.2
tokens/s
6.31
sec
pp1024+tg1024
340
tokens/s
31.2
tokens/s
3.05
sec
pp1280+tg3072
336
tokens/s
27.1
tokens/s
3.84
sec
pp384+tg1152
335
tokens/s
33.3
tokens/s
1.17
sec
pp64+tg1024
286
tokens/s
34.8
tokens/s
251
ms
pp16+tg1536
118
tokens/s
34.0
tokens/s
163
ms