Garnet Models
CantorAI Sign in

Model engineering by CantorAI

Selected AI models.
Tuned for the hardware you ship.

Garnet turns a focused set of capable open models into production packages for NVIDIA and Intel hardware—without a Python inference stack.

Download CantorOne Optimize my model
LLMVLMASRTTS
GARNET RUNTIMEENGINE READY
XMODEL IR PAGED KV NATIVE I/O
BackendTensorRT
PrecisionBF16 / INT4
ExecutionNative
01

Curated, not crowded

We select models with clear application value, then engineer each path for production.

02

Hardware-specific

Profiles are built for the backend, precision, memory, and latency target you actually deploy.

03

Application-ready

Validated manifests, native preprocessing, engine caching, and a stable serving interface.

Selected catalog

Four model paths.
One native runtime.

Choose an engineered package for your workload. Sign in to request access, review compatible profiles, or discuss a target we do not list yet.

LLM · TEXT GENERATION VALIDATED

Qwen3 1.7B

Compact language generation with native chat templating, paged KV cache, and optimized decode.

TensorRT BF16OpenVINO INT4CPU · GPU
31.87decode tok/s
i9-14900K · INT4
Request package →
VLM · IMAGE + TEXT ENGINEERING PREVIEW

Qwen3-VL 2B

Vision-language inference with native image preprocessing, MRoPE, continuous batching graphs, and paged KV.

TensorRT BF16NVIDIA GPUJPEG input
Request access →
ASR · SPEECH TO TEXT ENGINEERING PREVIEW

Qwen3-ASR 0.6B

Native WAV ingest, resampling, log-mel transform, audio encoding, and text decoding in one compiled path.

TensorRT BF1616 kHz inputNative frontend
Join preview →
TTS · TEXT TO SPEECH ENGINEERING PREVIEW

Qwen3-TTS 0.6B

CustomVoice generation with native codec reconstruction and 24 kHz waveform output.

TensorRT BF1624 kHz outputSpeaker selection
Join preview →

Garnet Runtime

Model code is not
a deployment plan.

Garnet captures a backend-neutral XLang tensor graph, validates it, and lowers it into an executable designed for the selected hardware.

  • ✓ Native C++ execution—no Python process at inference
  • ✓ TensorRT and OpenVINO lowering from one model graph
  • ✓ Paged KV memory, fixed decode buckets, and engine caching
  • ✓ Validated model manifests and application-facing APIs
Request a technical briefing →
COMPILED MODEL PIPELINE
01
Selected modelSafetensors + configuration
Qwen3
02
XModel graphBackend-neutral XLang IR
.x
03
Target profileBackend · precision · shape
JSON
NVIDIATensorRTGPU engines
INTELOpenVINOCPU / GPU

Try Garnet locally

One small starting point.
Only the models you choose.

Download the shared CantorOne desktop app first. Garnet runtimes and model packages stay separate, so a trial does not install every model or consume storage you did not choose.

Download CantorOne for Windows ↓ SHA-256 checksum →
Windows 10 / 11 · x64Portable preview~214 MB base app
EVALUATION FLOW4 STEPS
  1. 01
    Open CantorOne

    The shared desktop shell and Works experience start without a model bundle.

  2. 02
    Sign in to Garnet

    Your Garnet account connects evaluation access and trusted devices.

  3. 03
    Check this PC

    CantorOne identifies compatible hardware, backend, precision, and storage.

  4. 04
    Install one model

    Select a signed Garnet package, download it in the app, and run a local evaluation.

Already have CantorOne? Sign in →

Measured, not imagined

Performance with context.

Every number names the model, hardware, precision, and workload behind it.

NVIDIA · THROUGHPUT
527.9 tok/s

Qwen3-1.7B · batch 4

Masked continuous decode on RTX 4080 using official BF16 weights and GPU-resident paged KV storage.

INTEL · CPU INFERENCE
3.33×

Garnet vs. Ollama

31.87 vs. 9.56 decode tok/s on an i9-14900K, comparing Garnet INT4 with the tested Ollama package.

GarnetOllama
OUR STANDARD

Speed is only useful when the output stays useful.

Garnet validation records correctness, response quality, cold-load behavior, cache state, and unsupported hardware—not just the best token counter.

Ask for benchmark details →

Internal engineering measurements. Results vary by model, prompt, driver, operating system, and engine cache state. Comparisons are not precision-equivalent unless explicitly stated.

Custom model engineering

Your model.
Your hardware.
A measured path to production.

Have a model or device target outside the catalog? CantorAI can evaluate the graph, memory budget, precision strategy, native I/O path, and application packaging.

Start an optimization review →

Ready to run closer to the hardware?

Choose a Garnet model—or bring us yours.

Download CantorOneSign in to Garnet