Course comparison
Find the right next course.
Compare up to three published courses by skills, level, duration, prerequisites and certification requirements.
| Compare | Local LLM Engineering |
|---|---|
| Level | Intermediate |
| Duration | 18–26 study hours including labs |
| Format | Self-paced course |
| Access | Premium access |
| Skills | token embeddings, transformer blocks, LM head, weights, KV cache, context window, logits, next-token probabilities, sampling, autoregressive loop, key/value reuse, prefill vs decode, memory cost, latency intuition, prompt tokens, generated tokens, maximum context, truncation, long-context tradeoffs, Transformers local inference, quantized local runtimes, model formats at high level, GPU/CPU placement, tokens/sec, time-to-first-token, end-to-end latency, memory, prompt length effects, batching, OOM, slow generation, wrong dtype, tokenization mismatch, context overflow, repetition |
| Modules | 7 |
| Prerequisites | Transformers; Hugging Face; GPU engineering |
| Assessment | Course assessment |
| Certificate | Completion requirements apply |