NV RerankQA Mistral 3 4B is NVIDIA's reranking model. A 4B-parameter reranking model from NVIDIA built on Mistral 3, fine-tuned for question-answering retrieval reranking with strong multilingual performance.
Specifications
Canonical IDnvidia-nv-rerankqa-mistral-3-4b
TypeReranking
StatusActive
CreatorNVIDIANVIDIA
Input ModalitiesText
Parameters4B

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output0/5
Text·
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host NV RerankQA Mistral 3 4B, ranked by cheapest on-demand price. The model needs about 10 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NV4as_v4AzureAMD Radeon Instinct MI2516 GB$0.233/hrwestus2
g5g.xlargeAWST4g16 GB$0.420/hrus-east-1
Standard_NV8as_v4AzureAMD Radeon Instinct MI2516 GB$0.466/hrwestus2
7 more instances can run NV RerankQA Mistral 3 4B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Rerank 4 Fast33K$2.00Available
Rerank 4 Pro33K$2.50Available
Rerank 3.54KAvailable
Voyage Rerank 3.532KAvailable
NV RerankQA Mistral 3 4BCurrent
Rerank 3 English4KAvailable
Rerank 3 Multilingual4KAvailable
Voyage Rerank 2.532K$0.050Available
Voyage Rerank 2.5 Lite32K$0.020Available
BGE Reranker M3 28K$0.010$0.010Available
Jina Reranker 2 Base Multilingual1K$0.018$0.018Available

Model IDs

nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3
nvidia-nv-rerankqa-mistral-3-4b