Hands-On Large Language Models
  • Home
  • Start reading
  1. Consumer Hardware
  2. Follow-up plan
  • Overview
  • Foundations
    • 1. Introduction
    • 2. Tokens and embeddings
    • 3. Inside LLMs
  • Applications
    • 4. Text classification
    • 5. Clustering and topics
    • 6. Prompt engineering
    • 7. Advanced generation
    • 8. Semantic search
    • 9. Multimodal LLMs
  • Training
    • 10. Embedding models
    • 11. Fine-tuning BERT
    • 12. Fine-tuning generation
  • Consumer Hardware
    • Follow-up plan
    • 13. Local model stack
    • 14. Quantization and inference
    • 15. Serving models locally

On this page

  • Plan
    • Chapter 13: The Local Model Stack
    • Chapter 14: Quantization and Local Inference
    • Chapter 15: Serving Models Locally
    • Chapter 16: Modern Prompt Interfaces
    • Chapter 17: Retrieval That Holds Up
    • Chapter 18: LoRA and QLoRA Fine-Tuning
    • Chapter 19: LLMs as Predictive Models
    • Chapter 20: Preference Optimization on a Budget
    • Chapter 21: Evaluation Harnesses
    • Chapter 22: Tools and Agents
    • Chapter 23: Multimodal Local Models
    • Chapter 24: Deployment for One Person
  1. Consumer Hardware
  2. Follow-up plan

Follow-up Curriculum for Consumer-Hardware LLM Work

Plan

This follow-up sequence assumes a single consumer workstation: roughly 8-24 GB of VRAM, enough system RAM to memory-map larger quantized files, and a local stack built around llama.cpp, GGUF files, Hugging Face tools, and small PyTorch fine-tuning jobs.

Chapter 13: The Local Model Stack

Inventory the machine, the runtime, and the local model zoo before writing application code. The chapter teaches what model families, quantization formats, context windows, and memory budgets mean in practice.

Deliverable: a hardware/model inventory table and a practical fit estimate for the GGUF files already on disk.

Chapter 14: Quantization and Local Inference

Compare full-precision and quantized GGUF files, inspect metadata, and run small inference/latency tests. The goal is to connect quantization labels such as BF16, Q8_0, and Q4_K_M to file size, memory pressure, and throughput.

Deliverable: a local quantization comparison and a reproducible inference timing harness.

Chapter 15: Serving Models Locally

Start llama-server, query it through OpenAI-compatible HTTP endpoints, measure latency, and shut it down cleanly. This makes local models usable from normal application code.

Deliverable: a working local API server pattern using the GGUF stack in ~/tmp/llama-cpp.

Chapter 16: Modern Prompt Interfaces

Replace ad hoc prompting with typed interfaces: JSON schema, constrained decoding, retries, and validation.

Deliverable: a small extraction API with schema checks and regression tests.

Chapter 17: Retrieval That Holds Up

Build retrieval-augmented generation from separate pieces: chunking, embeddings, hybrid retrieval, reranking, prompt assembly, citations, and evals.

Deliverable: a local document QA system with retrieval metrics separated from generation metrics.

Chapter 18: LoRA and QLoRA Fine-Tuning

Train small adapters instead of full models. Cover target modules, rank, alpha, dropout, 4-bit loading, adapter merging, and export formats.

Deliverable: a QLoRA adapter for a 1B-8B model that fits consumer hardware.

Chapter 19: LLMs as Predictive Models

Use language-model infrastructure for structured prediction rather than chat. Compare classification heads, sequence classification, pairwise ranking, and listwise discrete choice against classical baselines.

Deliverable: a benchmark on the retail delivery choice data with conditional logit and neural-choice baselines.

Chapter 20: Preference Optimization on a Budget

Introduce DPO-style preference tuning and show when it is a better fit than supervised fine-tuning.

Deliverable: a small preference dataset, a tuned adapter, and a pairwise evaluation.

Chapter 21: Evaluation Harnesses

Make evaluation reproducible: golden sets, task metrics, judge prompts, pairwise comparisons, latency, memory, and cost.

Deliverable: a single evaluation runner that compares prompted, RAG, and fine-tuned systems.

Chapter 22: Tools and Agents

Treat agents as bounded workflow systems: typed tools, state, retries, logging, permissions, and human approval.

Deliverable: a local model driving a narrow, auditable tool workflow.

Chapter 23: Multimodal Local Models

Run small vision-language and embedding models locally. Cover OCR-like extraction, image search, captioning, and document understanding.

Deliverable: a local image/text retrieval and captioning notebook.

Chapter 24: Deployment for One Person

Version models, adapters, prompts, datasets, evals, and server settings. Track licenses and quant provenance.

Deliverable: a lightweight model-ops checklist and reproducible local deployment folder.

Back to top

Hands-On Large Language Models