AI Model Catalog | Inferbase

Provider	Model	In	Out	Context
DeepSeek	Deepseek R 1 Distill Llama 8B	text	text	131K
Microsoft	Phi 4 Multimodal Instruct	audio	text	131K
AI21 Labs	AI 21 Jamba Reasoning 3B	text	text	256K
Meta AI	Llama 3.2 1B	text	text	131K
Qwen	Qwen 3 Embedding 4B	text	text	41K
DeepSeek	Deepseek Moe 16B Base	text	text	-
Qwen	Qwen 2.5 VL 7B Instruct	textimage	text	131K
NVIDIA	Canary 1B Flash	audio	text	-
Meta AI	Llama 3.2 90B Vision	textimage	text	-
Meta AI	Codellama 13B Hf	text	text	16K
Technology Innovation Institute	Falcon H 1 1.5B Instruct GGUF	text	text	33K
Qwen	Qwen 3 VL Embedding 2B	text	text	-
Stability AI	Stablelm Base Alpha 3B	text	text	-
Microsoft	Resnet 18	text	text	-
NVIDIA	Nvidia Nemotron 3 Nano 30B A 3B FP 8	text	text	-
01.AI	Yi 1.5 9B Chat 16K	text	text	16K
NVIDIA	Nvidia Nemotron 3 Nano 30B A 3B NVFP 4	text	text	-
Stability AI	Stable Code 3B	text	text	-
Qwen	Qwen 3 VL 4B Instruct	textimage	text	-
Meta AI	Llama 2 13B Hf	text	text	4K
DeepSeek	Deepseek Math 7B Instruct	text	text	-
Qwen	Qwen 2.5 7B Instruct	text	text	33K
Technology Innovation Institute	Falcon H 1R 7B	text	text	-
Meta AI	Llamaguard 7B	text	text	4K
Qwen	Qwen2.5 Coder 7B Instruct	text	text	33K

Showper page

6of33

Run models directly through our API with smart routing

Describe your use case and get ranked recommendations

Calculate VRAM and compute requirements for self-hosting

Model Catalog