Is the Open Source AI Academy free?

Yes, 100% free. No sign-up, no credit card. All 18 modules, 31 lessons, and 73 quiz questions are accessible immediately. Your progress saves locally in your browser.

How is Infinity Open Source AI Academy different from vendor-specific open-weight tutorials?

Unlike generic or single-model tutorials, Infinity Tech Stack's Open Source AI Academy bridges global open weights (Llama 3.3, Mistral) and China Frontier Models (DeepSeek R1, Qwen 2.5, Kimi K3, GLM) with 18 comprehensive modules and simulated in-browser terminal labs for Ollama, llama.cpp, vLLM, and GGUF quantization. It requires zero GPU hardware, no cloud subscriptions, and no sign-up.

Does the Open Source AI Academy cover China's latest frontier open models?

Yes. The academy includes a dedicated China Frontier Models module covering Qwen, DeepSeek, Z.ai GLM, Moonshot Kimi, InternLM, Baichuan, and Yi, plus a practical model-radar workflow for weekly tracking and gated production adoption.

Did Kimi K3 score higher than Claude?

On several benchmarks, yes. Kimi K3 (July 14, 2026: 2.8T open-weight MoE, 1M context) beat Claude Fable 5 on 6 of 14 shared benchmarks — including BrowseComp (91.2 vs 88.0), SWE Marathon (42.0 vs 35.0), and Terminal-Bench 2.1 (88.3 vs 84.6) — topped the Arena.ai Frontend Code Arena, and edged Claude Opus 4.8 on the Artificial Analysis Intelligence Index (57 vs 56) at about 3.3x lower pricing. Claude Fable 5 won the other 8 benchmarks and leads that index at 60. The academy's China Frontier Models module has a dedicated lesson on the full scoreboard.

What topics does the Open Source AI Academy cover?

The course covers Transformer architecture, Meta Llama 4, Mistral, DeepSeek, Qwen, Gemma, Hugging Face, quantization (GGUF, AWQ, GPTQ, EXL2), Ollama, llama.cpp, vLLM, SGLang, LoRA/QLoRA fine-tuning, pre-training from scratch, RLHF/DPO/GRPO alignment, and production MLOps with Docker and Kubernetes.

vLLM is the industry-standard engine for high-throughput production LLM serving. It uses PagedAttention for efficient GPU memory management and continuous batching for >90% GPU utilization.

Do I need expensive hardware to run open-source models?

No. Many models can run on consumer GPUs (e.g., RTX 4090) or even CPUs via llama.cpp. The course covers deployment strategies for every budget, from Raspberry Pi edge devices to multi-GPU production clusters.

Does the Open Source AI Academy include hands-on labs?

Yes. Hands-on terminal labs are built into the lessons - ollama pull, run, and list models, quantize a model to Q4_K_M, and serve it with vLLM using real, vendor-verified commands, with objectives, hints, solutions, and XP rewards. No GPU or sign-up needed.

Which Ministral model can run on a Raspberry Pi?

Ministral 3B — Ministral 3B at Q4 quantization needs only ~2GB RAM, making it suitable for Raspberry Pi and IoT devices.

Codestral & Edge Models Tutorial | The Mistral Ecosystem

[ ABORT TO HUD ]

SEQ. 1

SEQ. 2

Codestral & Edge Models

🌬️ The Mistral Ecosystem⏱ 8 min⭐ 75 BASE XP⌨ HANDS-ON LAB

Specialized Mistral Models

Codestral 2: The Coding Specialist

A 22B dense model purpose-built for code generation and agentic coding workflows. Key features:

Optimized for code completion, refactoring, and multi-file edits
Supports tool calling for agentic development
Re-licensed to Apache 2.0 (earlier versions had restrictive licenses)
Integrated into IDEs: Cursor, Continue.dev, VS Code

Ministral: Edge AI

The Ministral family (3B, 8B, 14B) is designed for deployment on constrained hardware:

Model	RAM Needed	Best For
Ministral 3B	~2GB (Q4)	Mobile, IoT, Raspberry Pi
Ministral 8B	~5GB (Q4)	Laptops, desktops
Ministral 14B	~8GB (Q4)	Workstations, light servers

Mistral Small 4: The Hybrid

Released April 2026, this model unifies instruct, reasoning, and coding in a single multimodal package. It's the "Swiss Army knife" of the Mistral ecosystem - small enough for consumer GPUs but capable enough for production use.

🐳 Container Pattern: For edge deployments, use Ollama in a Docker container:
docker run -d --gpus all -v ollama:/root/.ollama -p 11434:11434 ollama/ollama
Then: docker exec -it [container] ollama run ministral:8b

⌨ HANDS-ON LABQuery Codestral Fill-in-the-Middle (FIM)

⭐ +200 XP

Use Mistral Codestral's native Fill-in-the-Middle capability to complete code between prefix and suffix markers.

1Send a FIM generation request to the local endpoint specifying prompt prefix and suffix.

lab-sandbox — simulated environment

INFINITY LAB SANDBOX v2.6 — simulated shell
Type the command for the current objective. Helpers: "hint", "solution", "clear".
$

OBJECTIVE 1 / 1 — type "hint" if stuck

KNOWLEDGE CHECK

QUERY 1 // 2

What was the key licensing change for Codestral 2?

Changed to GPL

Re-licensed to Apache 2.0 for commercial use

Became fully proprietary

Added per-token pricing