/
Recipes
Docs
GitHub
Providers
Arcee AI
Ernie (Baidu)
Seed (ByteDance)
DeepSeek
Google
inclusionAI
InternLM
Jina AI
Meituan LongCat
Meta
Microsoft
MiniMax
Mistral AI
Moonshot AI
NVIDIA
OpenAI
InternVL (OpenGVLab)
PaddlePaddle
Qwen
Stability AI
StepFun
Tencent Hunyuan
Wan AI
Xiaomi MiMo
GLM (Z-AI)
Meta
meta-llama
·
3 recipes
HuggingFace
Text
3
Llama-4-Scout-17B-16E-Instruct
109B / 17B
moe
BF16
262G
FP8
131G
NVFP4
65G
v0.12.0+
→
Llama-3.3-70B-Instruct
70B
dense
BF16
170G
FP8
84G
NVFP4
42G
v0.12.0+
→
Llama-3.1-8B-Instruct
8B
dense
BF16
20G
NVFP4
5G
FP8
10G
v0.6.0+
→
