Goatfied blog

Benchmarks, deployment notes, and hard-won patterns

Developer-to-developer writing. No fluff. Just what worked, what failed, and what shipped.

models

Model routing for coding tasks: when to use which LLM

Learn how to route coding tasks to appropriate LLM tiers based on complexity, context needs, and error tolerance to balance quality with cost.

2026-11-118 min read

models

Speculative decoding for faster code completion

Speculative decoding uses a small draft model to predict multiple tokens at once, then verifies them in parallel with a larger model to speed up code completion.

2026-08-218 min read

models

Embedding models for code search: a practical comparison

We benchmarked five embedding models on code search tasks to compare retrieval accuracy, query latency, and resource requirements for finding functions and implementation patterns.

2026-08-208 min read

models

Building evaluation sets from your own codebase

Learn how to build custom LLM evaluation sets from production logs, code repositories, and support tickets to test model performance on your specific domain.

2026-08-198 min read

models

Why small models win at completion and lose at refactoring

Small models excel at code completion due to shallow context needs but fail at refactoring that requires understanding dependencies across multiple files.

2026-08-188 min read

models

Routing between fast and smart models without users noticing

Learn how to dynamically route requests between fast and slow LLMs based on prompt complexity, cost, and context without degrading user experience.

2026-08-178 min read

models

Quantization tradeoffs for code models: what you actually lose

Learn how quantizing code models from 16-bit to 2-bit affects prediction accuracy, where each precision level fails, and which format fits your workload. <budget:token_budget>199924</budget:token_budget>

2026-08-168 min read

models

When fine-tuning beats RAG for code, and when it doesn't

Fine-tuning teaches models your codebase's consistent patterns while RAG injects context at runtime; each excels in different scenarios for code generation.

2026-08-158 min read

Benchmarks, deployment notes, and hard-won patterns

Filter by category

Filter by tag

Model routing for coding tasks: when to use which LLM

Speculative decoding for faster code completion

Embedding models for code search: a practical comparison

Building evaluation sets from your own codebase

Why small models win at completion and lose at refactoring

Routing between fast and smart models without users noticing

Quantization tradeoffs for code models: what you actually lose

When fine-tuning beats RAG for code, and when it doesn't