TEST #1421 RESULTS
08/24/2025 - 1:01 PM
ACCELERATOR
MODEL
63.1
tokens/s
generation
385
ms
time to first token
3625
tokens/s
prompt
841
LocalScore
HOW YOU STACK UP
Explore All Resultscodellama_codellama-7b-instruct-hf - Q5_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.3GB
OS
Linux
Kernel Release
6.16.1-arch1-1
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Fri, 15 Aug 2025 16:04:43 +0000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4185
tokens/s
67.3
tokens/s
260
ms
pp4096+tg256
2959
tokens/s
52.3
tokens/s
1.40
sec
pp2048+tg256
3794
tokens/s
61.1
tokens/s
555
ms
pp2048+tg768
3889
tokens/s
59.4
tokens/s
543
ms
pp1024+tg1024
4542
tokens/s
64.3
tokens/s
240
ms
pp1280+tg3072
4440
tokens/s
57.7
tokens/s
304
ms
pp384+tg1152
4882
tokens/s
67.6
tokens/s
93
ms
pp64+tg1024
3006
tokens/s
69.5
tokens/s
35
ms
pp16+tg1536
928
tokens/s
68.4
tokens/s
31
ms