Home
Latest Results
Download
About
Blog
Model Hf
Q8_0
4.6B
params
COMPARE ACCELERATORS
1 accelerators tested
Select Accelerators
NVIDIA GeForce RTX 4090
24GB
Model Hf - Q8_0
Prompt tokens/s
Generation tokens/s
Time to First Token (ms)
LocalScore
LEADERBOARD
GPU
CPU+GPU
CPU
ACCELERATOR
PROMPT
GENERATION
TTFT
LOCALSCORE
NVIDIA GeForce RTX 4090
GPU / 24GB
PROMPT
11064
tokens/s
GENERATION
68.1
tokens/s
TTFT
115
ms
LOCALSCORE
1873