NINFEREZ CONVERTER

From checkpoint
to ready-to-run.

Prepare supported models for NInfer with a guided desktop workflow. Start in Manager, or use the independent Windows Converter.

Windows x64 · CPU-only conversion · Portable 1.0.0

NInferEZ Converter logoPREPARE · INSPECT · CONVERT
EXPLORE THE PROJECTConverter on GitHub ↗Models on Hugging Face ↗
GUIDANCE WHEN YOU WANT IT

A clear path from source to artifact.

01

Choose a source.

Select a compatible local checkpoint, supported GGUF, or a qualified NInfer container.

02

Attach resources.

Match the configuration, tokenizer, and optional components required by your source.

03

Review your plan.

Inspect supported profiles and output choices. Compatibility checks explain missing files.

04

Convert with clarity.

Follow progress, cancel when needed, and inspect the resulting NInfer artifact.

TWO WAYS TO WORK

A helpful wizard.
Room for the details.

Guided mode walks through the source, compatibility, plan, and destination. Manual mode exposes profiles, components, mappings, tensor policies, and chunk or shard limits.

Both use the same backend. Import and export requests to keep advanced plans reusable.

Supported checkpointConfiguration + tokenizer
↓
Compatibility & conversion planGuided wizard or manual controls
↓
NInfer v3 artifactStructural validation
KNOW YOUR INPUTS

Designed for supported geometry.

Compatibility comes from source geometry, tensor encodings, and importer coverage.

Checkpoint sources

Compatible Qwen3.5 Dense/MoE geometry, including supported Qwen3.6 and Qwen3.8 derivatives. Safetensors checkpoints and indexed shards need matching resources.

Compressed inputs

Supported native NVFP4, row- or tensor-scaled FP8, and supported GGUF encodings. Higher-bit output cannot restore information lost in compression.

Optional components

Vision, MTP, and DFlash/DFlash2 when compatible companion sources are provided. Structural checks are separate from GPU execution or quality evaluation.

No separate Python, .NET, or CUDA Toolkit for end users.

The standalone Portable includes its CPU conversion runtime and works with offline local sources. Conversion uses CPU, RAM, and disk. Optional GPU engine testing is selected explicitly.

YOUR NEXT STEP

Put your GPU to work.

Your models, your workspace, your next idea.
Start with NInferEZ Manager.

Windows x64 · Installer or Portable