open-source · on-device AI
mindpool@local:~$ ./learn --target=real-ai

Build real AI on your own hardware

Not another course on calling a frontier API. mindpool teaches the full local lifecycle — run, ground, fine-tune, and ship open models you actually control.

// get the toolchain
$ curl -fsSL mindpool.io/install | sh
macOS · Linux · Windows (WSL2)
// or, on macOS (Apple Silicon)
$ brew install --cask mindpool-labs/tap/mpl
detected Apple M3 Max · 64GB unified — tier T3
installed ollama · llama.cpp · mlx-lm (pinned)
pulled Qwen3-8B · Q4_K_M · 4.7GB
fine-tune env ready — unsloth + trl
enrollment verified on-chain — 0x9f…2aE
module 09 · quantization — unlocked
$ cat ./what-you-actually-learn

The on-device lifecycle, end to end

Every module maps to a real step you run locally — no hand-waving, no "it just works."

01 → 02
Source & run
Read model cards on HF, run GGUF locally, expose a local API.
03 → 05
Prompt, ground & tools
Chat templates and sampling, RAG retrieval, then tool-use agent loops.
06 → 08
Data, tune & evaluate
Curate datasets, LoRA/QLoRA → GGUF with Unsloth, then score on an eval harness.
09 → 10
Optimize & ship
imatrix Q4_K_M quants, serve for throughput, package and hand off.
$ df -h ./hardware

Pick the rig that runs the work

Bandwidth, not capacity, sets your tokens/sec. Cloud-spot is the relief valve for the rare 70B full tune.

› the buyer's guide — 4 tiers