AI Model Catalog | Inferbase

Provider	Model	In	Out	Context
NVIDIA	Alpamayo 1.5 10B	-	-	-
Microsoft	Phi 3.5 Mini Instruct	text	text	128K
Meta AI	Meta Llama 3 70B	text	text	-
Black Forest Labs	Flux.2 Dev	image	image	-
Technology Innovation Institute	Falcon Mamba Tiny Dev	text	text	33K
Meta AI	Llama 2 70B Hf	text	text	4K
NVIDIA	Qwen 3.5 397B A 17B NVFP 4	text	text	-
Technology Innovation Institute	Falcon H 1 1.5B Instruct	text	text	33K
DeepSeek	Deepseek Coder 1.3B Base	text	text	16K
Meta AI	Llama 3.1 8B	text	text	-
Black Forest Labs	Flux.2 Klein 9B Kv Fp 8	image	image	-
Black Forest Labs	Flux.2 Klein Base 9B Fp 8	image	image	-
Qwen	Qwen 2.5 0.5B	text	text	131K
Meta AI	Llama 4 Scout 17B 16E	textimage	text	262K
AI21 Labs	AI 21 Jamba Mini 1.5	text	text	256K
Technology Innovation Institute	Falcon H 1 34B Base	text	text	33K
Qwen	Qwen 3 4B	text	text	41K
Meta AI	Llama 3.1 405B Instruct FP 8	text	text	-
NVIDIA	Bigvgan_v 2_44khz_128band_512x	audio	audio	-
NVIDIA	Nemotron 3 Nano Omni 30B A 3B Reasoning NVFP 4	-	-	-
Microsoft	Vibevoice ASR	audio	text	-
DeepSeek	Deepseek Coder 1.3B Instruct	text	text	16K
01.AI	Yi 34B	text	text	4K
AI21 Labs	Jamba Tiny Dev	text	text	-
Microsoft	Deberta V 3 Small	text	text	-

Showper page

7of33

Inference API

Run models directly through our API with smart routing

Model Recommender

Describe your use case and get ranked recommendations

GPU Capacity Planner

Calculate VRAM and compute requirements for self-hosting

Showing 25 of 821 models

Updated May 5, 2026

Alpamayo 1.5 10B

NVIDIA

Phi 3.5 Mini Instruct

Microsoft

128K ctx

text

Meta Llama 3 70B

Meta AI

text

Flux.2 Dev

Black Forest Labs

image

Falcon Mamba Tiny Dev

Technology Innovation Institute

33K ctx

text

Llama 2 70B Hf

Meta AI

4K ctx

text

Qwen 3.5 397B A 17B NVFP 4

NVIDIA

text

Falcon H 1 1.5B Instruct

Technology Innovation Institute

33K ctx

text

Deepseek Coder 1.3B Base

DeepSeek

16K ctx

text

Llama 3.1 8B

Meta AI

text

Flux.2 Klein 9B Kv Fp 8

Black Forest Labs

image

Flux.2 Klein Base 9B Fp 8

Black Forest Labs

image

Qwen 2.5 0.5B

Qwen

131K ctx

text

Llama 4 Scout 17B 16E

Meta AI

262K ctx

textimage

AI 21 Jamba Mini 1.5

AI21 Labs

256K ctx

text

Falcon H 1 34B Base

Technology Innovation Institute

33K ctx

text

Qwen 3 4B

Qwen

41K ctx

text

Llama 3.1 405B Instruct FP 8

Meta AI

text

Bigvgan_v 2_44khz_128band_512x

NVIDIA

audio

Nemotron 3 Nano Omni 30B A 3B Reasoning NVFP 4

NVIDIA

Vibevoice ASR

Microsoft

audiotext

Deepseek Coder 1.3B Instruct

DeepSeek

16K ctx

text

Yi 34B

01.AI

4K ctx

text

Jamba Tiny Dev

AI21 Labs

text

Deberta V 3 Small

Microsoft

text

Provider	Model	In	Out	Context
NVIDIA	Alpamayo 1.5 10B	-	-	-
Microsoft	Phi 3.5 Mini Instruct	text	text	128K
Meta AI	Meta Llama 3 70B	text	text	-
Black Forest Labs	Flux.2 Dev	image	image	-
Technology Innovation Institute	Falcon Mamba Tiny Dev	text	text	33K
Meta AI	Llama 2 70B Hf	text	text	4K
NVIDIA	Qwen 3.5 397B A 17B NVFP 4	text	text	-
Technology Innovation Institute	Falcon H 1 1.5B Instruct	text	text	33K
DeepSeek	Deepseek Coder 1.3B Base	text	text	16K
Meta AI	Llama 3.1 8B	text	text	-
Black Forest Labs	Flux.2 Klein 9B Kv Fp 8	image	image	-
Black Forest Labs	Flux.2 Klein Base 9B Fp 8	image	image	-
Qwen	Qwen 2.5 0.5B	text	text	131K
Meta AI	Llama 4 Scout 17B 16E	textimage	text	262K
AI21 Labs	AI 21 Jamba Mini 1.5	text	text	256K
Technology Innovation Institute	Falcon H 1 34B Base	text	text	33K
Qwen	Qwen 3 4B	text	text	41K
Meta AI	Llama 3.1 405B Instruct FP 8	text	text	-
NVIDIA	Bigvgan_v 2_44khz_128band_512x	audio	audio	-
NVIDIA	Nemotron 3 Nano Omni 30B A 3B Reasoning NVFP 4	-	-	-
Microsoft	Vibevoice ASR	audio	text	-
DeepSeek	Deepseek Coder 1.3B Instruct	text	text	16K
01.AI	Yi 34B	text	text	4K
AI21 Labs	Jamba Tiny Dev	text	text	-
Microsoft	Deberta V 3 Small	text	text	-

Showper page

7of33

Inference API

Run models directly through our API with smart routing

Model Recommender

Describe your use case and get ranked recommendations

GPU Capacity Planner

Calculate VRAM and compute requirements for self-hosting

Model Catalog

Explore More

Inference API

Model Recommender

GPU Capacity Planner

Start building with the right model.

Explore More

Inference API

Model Recommender

GPU Capacity Planner