n4nAI

Topic

Model Parameters & Model Size

7 posts on model parameters & model size — part of glossary on the n4n AI blog.

GlossaryDefinition

What are LLM parameters, exactly?

A precise technical explanation of LLM parameters — what they are, how they function in transformer architectures, why parameter count correlates with capability, and the misconceptions that trip up engineers.

5 min read
GlossaryDefinition

LLM parameters explained: what a "70B" model means

What "70B" means in LLM model names, how parameter counts map to memory and compute, and what engineers actually need to know when choosing model sizes.

6 min read
GlossaryAnalysis

How VRAM requirements scale with parameter count

A practical breakdown of how model parameters translate to GPU memory, covering quantization, KV cache, and real-world GPU fit.

5 min read
GlossaryAnalysis

How model size affects inference cost and speed

Understand how model size drives inference latency, memory pressure, and per-token cost — with concrete math and routing strategies for production workloads.

4 min read
GlossaryAnalysis

How many parameters does GPT-4 have? What's known

GPT-4's parameter count remains undisclosed by OpenAI. We examine the evidence, architectural clues, and why the number matters less than you think.

7 min read
GlossaryAnalysis

Does a bigger model always mean a better model?

Analysis of when larger LLMs outperform smaller ones, covering scaling laws, diminishing returns, inference costs, and practical routing strategies for engineers.

4 min read
GlossaryComparison

7B vs 70B vs 405B: what model size actually changes

A practitioner's comparison of 7B, 70B, and 405B LLMs across capabilities, cost, latency, deployment, and ecosystem — with a clear verdict for each use case.

7 min read