TEST #2353 RESULTS
01/25/2026 - 6:20 PM
ACCELERATOR
MODEL
260
tokens/s
generation
87
ms
time to first token
15534
tokens/s
prompt
3592
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-10310U CPU @ 1.70GHz (skylake)
RAM
62.1GB
OS
Linux
Kernel Release
6.14.0-37-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #37~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 20 10:25:38 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
20873
tokens/s
256
tokens/s
53
ms
pp4096+tg256
13138
tokens/s
222
tokens/s
316
ms
pp2048+tg256
17188
tokens/s
237
tokens/s
123
ms
pp2048+tg768
17188
tokens/s
245
tokens/s
123
ms
pp1024+tg1024
19835
tokens/s
259
tokens/s
55
ms
pp1280+tg3072
19565
tokens/s
244
tokens/s
69
ms
pp384+tg1152
20864
tokens/s
278
tokens/s
22
ms
pp64+tg1024
9282
tokens/s
288
tokens/s
10
ms
pp16+tg1536
1874
tokens/s
311
tokens/s
13
ms