VeizikNVIDIA and Apple Silicon builds are available now.Release notes →
veiziknative inference engine
Sign inDownload
Product
OverviewWhat the engine isHow it worksWeights in, native execution outPlatformsNVIDIA · Apple SiliconSecurity & licensingDevice-bound, local by designReleasesEvery build, dated
Engineering
All capabilitiesOne researched page per capabilityVideo memory720p that stays under a 24 GB cardA 35B model on one card21 GiB resident on a 24 GB GPUEdge optimizationGenerative AI on a Raspberry Pi CPUIts own stackNo Python, no framework, no cuBLASResume a renderCrash, resume, same result
Models
NVIDIALanguage and video — available nowApple SiliconQwen2.5 · Qwen3 — availableRaspberry Pi · edgeSD1.5 · SDXS · GPT-2 — arriving soonFull catalogueEvery model and its status
Hardware
All hardwareEvery device × every modelPick your deviceWhat runs on yoursNVIDIAAmpere → Blackwell · CUDAApple SiliconM1 – M4 · MetalRaspberry Pi · edgeCPU & NPU — generative AI on a Pi
Benchmarks
All resultsMatrix or pick, by buildBuilds & downloadsEvery build, JSON / CSVMethod & notationHow every figure is taken
Docs
QuickstartInstall to first runCommand referenceEvery documented commandActivate a machineDevices and licenceWhat leaves the machineOffline and networkTroubleshootingWhen something fails
GalleryReleasesSign inDownloadGitHub
← Models
Language · Platform announced with the release

SmolLM2

Run SmolLM2 in veizik's native edge runtime on a Raspberry Pi CPU — no GPU, no Python. Weights are user-supplied from the publisher, not shipped.

Status
Coming
Platform
Platform announced with the release
Class
Language
Publisher
Hugging Face
Architecture
smollm2
Weights
Supplied by you
Guide

Availability

Run instructions publish with the release.

No download is open for this family yet, so there is nothing to install or pull.

Support

Where it runs.

Evidence and availability are separate: a verified device is not a download, and an available model is not verified on every device.

VerifiedVerifiedRun end to end on this exact device, on a published build.Architecture-supportedArchitecture-supportedVerified on another device of the same architecture; this device itself is untested.Expected, untestedExpected, untestedThe engine targets this architecture; nobody has run this model on it. No claim is made.In preparationIn preparationNo build is downloadable yet, and no figure is offered.Not offeredNot offeredThis family is not offered on this platform.UnknownUnknownNo information yet — the platform is announced with the release.
FamilyRTX 3080 TiRTX 3090RTX 4090RTX 5090RTX A5000A40A100 80GB PCIeA100-SXM4-80GBH100 80GB HBM3RTX PRO 4500 BlackwellM4 ProM1 UltraM1 MaxM2 Pro
SmolLM2
all variants		Not offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offeredNot offered

Availability by variant

Model idAvailabilityPlatformContextWeights in memory
smollm2-135mNot publishedRaspberry Pi · edge——
smollm2-360mNot publishedRaspberry Pi · edge——

“Verified” means this family ran end to end on that exact device, on a published build. Architecture membership never upgrades a device to verified.

Variants

2 checkpoints

Model idSizeCheckpointOn diskContextWeights in memory
smollm2-135m135MHuggingFaceTB/SmolLM2-135M———
smollm2-360m360MHuggingFaceTB/SmolLM2-360M———
Performance

Performance

Figures publish with the release that runs it.

Licence

Weights and terms

SmolLM2 weights are published by Hugging Face under Apache-2.0 and are supplied by the user, not shipped. Veizik ships only the inference engine and neither redistributes nor relicenses the weights.

Full licence terms →

Other models linked in the sidebar:

Stable Diffusion 3.5: Powered by Stability AI HunyuanImage: Weights are not included. Model availability and use are governed by the model provider's license and regional restrictions.