self-hosted
/ai
GPUs
Models
Compare
Tools
Search
⌘K
§01
·
spec · /gpus
RTX 4070 Ti Super
nvidia
40 series
16GB VRAM
models (3)
§02
·
models that run on this GPU
3 total
Model
Vertical
Best speed
Min VRAM
Works
Benchmarks
gpt-oss 20B
llm
128.9
tokens/s
16
GB
✓
2
check ↗
Qwen3-8B
llm
96.3
tokens/s
16
GB
✓
2
check ↗
Qwen3 14B
llm
58.1
tokens/s
16
GB
✓
2
check ↗