TEST #937 RESULTS
05/24/2025 - 1:35 AM
ACCELERATOR
MODEL
374
tokens/s
generation
43
ms
time to first token
30896
tokens/s
prompt
6431
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen Threadripper 3970X 32-Core Processor (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
6.8.0-60-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #63-Ubuntu SMP PREEMPT_DYNAMIC Tue Apr 15 19:04:15 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
43851
tokens/s
403
tokens/s
26
ms
pp4096+tg256
26079
tokens/s
313
tokens/s
161
ms
pp2048+tg256
37856
tokens/s
369
tokens/s
57
ms
pp2048+tg768
37499
tokens/s
356
tokens/s
57
ms
pp1024+tg1024
43319
tokens/s
379
tokens/s
26
ms
pp1280+tg3072
40032
tokens/s
348
tokens/s
35
ms
pp384+tg1152
36970
tokens/s
397
tokens/s
13
ms
pp64+tg1024
9232
tokens/s
412
tokens/s
9
ms
pp16+tg1536
3224
tokens/s
392
tokens/s
7
ms