Documentation

Set up SharpMind anywhere.

The same Studio, the same model format, four places to run it. Start with the machine in front of you; add a GPU host when a fine-tune needs more memory. Every guide includes the errors you are likely to see and what they mean.

Watch

SharpMind Studio in 60 seconds

A quick tour of the local-first workbench: models, chat, Work, training and Labs. The playlist carries the longer walkthroughs.

YouTube · playlist · @Integral2u
GPU · SSH

Vultr + SSH setup

Create the instance, add one key, and let Studio install Docker, the NVIDIA toolkit and the server image.

recommended for a first GPU run
Local

Local Docker

Build the Compute image on this PC (or the GPU server image) and start it from Settings.

no account · CPU or local NVIDIA GPU
Cloud

Runpod

Deploy a GPU pod through the Runpod API and terminate it when the run is done.

API key · Docker Hub · proxy URLs
Models

HuggingFace

Browse GGUF repositories, check licence and size, download with resume and convert to .smm.

public downloads · token for gated
Remote models

OpenRouter

Connect hosted models for Chat and Work with an encrypted key and local tool permissions.

inference only · per token
Projects

Work mode

Project context, scoped file and web tools, skills and explicit read/write/delete permissions.

local or OpenRouter
Labs

Model labs

Layer importance, quantization, activation maps, latent space, architecture templates and agent definitions.

measure before you change the weights
Configuration

Settings

Appearance, system tools and plugins, family and model defaults, providers and pairing.

defaults flow down; overrides win
Access

Phone pairing

Open the local Studio from a phone on your LAN with a QR or PIN, then revoke the device when you are done.

LAN only · revocable tokens
Overview

Compare providers

Local Docker, Runpod, Vultr or your own Linux box: cost, ports and who runs the setup.

start here if you are unsure
Train

Pretrain, LoRA and SFT

Which jobs use the GPU, which stay on the CPU, and why a LayerNorm base falls back.

GPU fine-tuning: LoRA only
Errors

Troubleshooting

Pull access denied, accelerator declined, firewall timeouts, SSH auth, 401 after a token rotation.

the exact messages
What works today

The support matrix.

This PC covers the Studio process and an optional Local Docker host on the same machine. A local NVIDIA GPU is used only when the GPU image and Docker runtime are present. A Compute host always brings its own device.

CapabilityThis PC / Local DockerCompute hostNotes
Chat with a packaged modelYesYesOne active model per process on a host.
OpenAI-style API—YesBearer token; /v1/chat/completions, models, files, training jobs.
Pretrain from scratchYes (CPU)Yes (CPU)The GPU engine refuses whole-weight training by design.
Layer importance labYes-Model-agnostic per-block attention/FFN ablation with activation RMS and loss deltas; source builds.
LFM3-VL image inputYes-Attach an image in Chat when the vision mmproj is next to the model; the native tower and 2x2 merge projector describe it. Source builds.
LoRA fine-tuneYes (GPU or CPU)Yes (GPU or CPU)GPU needs RMSNorm + RoPE/NoPE + gated FFN; otherwise the CPU retry runs.
SFT (assistant-only loss)Yes (GPU or CPU)Yes (GPU or CPU)Chat JSONL; the base supplies the tokenizer and template.
GPU inferenceWith a supported local GPUYes (GPU or CPU)Also covers LayerNorm and dense-GELU models.
Local chat artifactsSend / render / micNot yetImages, audio, files and code. LFM3-Audio microphone and audio attachments transcribe locally.
LFM3 text (13 conv / 5 SWA / 6 global)SmokeSmokeLayer map, per-head gate and templated chat validated; broad quality pending.
ASR / TTSASR and TTSNoNative LFM3-Audio encoder, MaskGIT depth decoder and LiquidCodec via mmproj; long recordings are chunked and speech is written as a 24 kHz WAV.
Remote data and artifacts—YesUploads with progress; exports download back to Studio.
Version 1.1.2. The repository is the source of truth. The server image contract is stable; later releases may still adjust screens or flags.
FIVE-MINUTE PATH

Just want to see it run?

Build the app, pick a GGUF or .smm, and chat locally. No account and no host.

GPU PATH

Want a real fine-tune?

Rent an A16, add one SSH key, and let the Compute card install and deploy the GPU image.