Qwen3 4B Thinking 2507
Q8_0
4.4Bparams
COMPARE ACCELERATORS
1 accelerators tested
Select Accelerators
NVIDIA GeForce RTX 4070 Laptop GPU
8GB
Qwen3 4B Thinking 2507 - Q8_0
LEADERBOARD
GPU / 8GB
PROMPT
2865
tokens/s
GENERATION
41.0
tokens/s
TTFT
513
ms
LOCALSCORE
612
