Modules / 04 · Models
Live · Free forever

Every open
AI model.
One place.

Browse, compare and download every meaningful open-source model. Free. One-command local setup. Or skip the install and run them on our cloud at-cost — Mumbai & Chennai mirrors mean 10× faster downloads.

Catalog2,400+ models · updated daily
MirrorsBLR · MUM · CHN
RunnersOllama · llama.cpp · Docker
HostedAPI · pay per call
Download adris.tech — Free Windows · macOS coming soon
// Model Hub · open source catalogue — models · tiny to frontier
models shown
Loading models…
01One-command setup
Ships with App Release

Zero config.
One line.

No .exe chaos. No fifteen-step install. Open adris.tech, pick a model, click Download — Ollama is auto-configured behind the scenes. You'll be talking to the model in under 90 seconds.

  • Auto-detects your hardware — picks the right quantisation
  • Works on Windows via the built-in Ollama runner
  • Verifies download integrity with checksums
  • Browse without signup — download only requires an account
// install · deepseek-r1:7b ~90s to first token
$ curl -fsSL https://ollama.com/install.sh | sh && ollama run deepseek-r1:7b
→ detecting hardware… 16GB RAM · GPU found
→ selecting deepseek-r1-q4_k_m · 4.7 GB
→ downloading from adris.tech hub…
→ checksum verified · loading…
✓ ready · type a prompt
02Compare
Available in App

Pick the right
model. Before you
commit.

Select two or three models, run the same prompt against all of them, see the outputs side-by-side with timing and cost. Stop guessing which one is best for your use case.

  • Up to 4 models in parallel
  • Same prompt, same temperature, same seed
  • Latency, cost, and output length tracked
  • Share a comparison link with your team

Live comparison · inside the app

Download two or more models. Type a prompt. adris.tech runs them on your machine — one by one, or all at once if your RAM supports it — and shows the real outputs side by side with timing.

01Download models from the hub above
02Open Compare tab · select 2–4 models
03Type your prompt · hit Compare
04Real outputs · real timing · no fake data
Download adris.tech — Free
03Bring your own key
Live Now

No GPU?
Use the cloud.

Plug in your own OpenAI, Gemini, or Claude API key in Connect Apps. adris.tech routes Krew, Coder, and Guard through your key — at provider cost, zero markup. Your key, your bill, your data.

  • OpenAI · Gemini · Claude — all supported
  • One-time setup in Connect Apps · works instantly
  • Provider pricing directly — ₹0 adris.tech markup
  • Keys stored in Windows Credential Manager — never in plaintext
// Connect Apps → Add key → done
Step 1: Open adris.tech → Connect Apps
Step 2: Paste your OpenAI / Gemini / Claude key
Step 3: Hit Save & Test

adris.tech pings the provider to verify the key,
then stores it in Windows Credential Manager.
// ✓ connected · all AI features unlocked
{ "status": "connected",
  "provider": "openai",
  "model": "gpt-4o" }
Model Input / 1k tok Output / 1k tok
DeepSeek V3 ₹0.04 ₹0.12
Llama 3.3 70B ₹0.06 ₹0.18
Sarvam-1 Indic ₹0.02 ₹0.06
Claude Sonnet 4.5 ₹0.24 ₹1.20
04Collections

Curated by us.
Updated weekly.

Browsing 2,000+ models is paralysis. Our team publishes short lists for the situations you'll actually face. "Best models for Hindi". "Runs on 8 GB RAM". "Free coding model that beats GPT-4". Curated, opinionated, current.

Collection · 12 models

Indian language stars

Best models with Hindi, Tamil, Telugu, Bengali support — ranked by BLEU on IndicGenBench.

Browse collection →
Collection · 8 models

Runs on 8 GB RAM

Smaller quantised models that fit in a typical Indian dev laptop without a discrete GPU.

Browse collection →
Collection · 6 models

Free coding heroes

Open models that match or beat closed models on HumanEval and SWE-bench at zero cost.

Browse collection →
Collection · 10 models

Fast & tiny

Sub-3B models for edge devices, mobile, and embedded use. Latency under 100ms.

Browse collection →

Browse all models.
Free, forever.

No signup needed to browse and download. Sign up only when you want hosted inference or to save your collections.