LLM Evaluation & Benchmarking10 min read• Published August 01, 2026

RAG Evaluation Frameworks & LLM Serving Metrics: TTFT, Throughput, Latency & VRAM Sizing

RAGAS triad metrics alongside operational serving parameters: Time To First Token, decode speed, throughput trade-offs, and VRAM memory math.

YP
Yashika P
Founder @ AscendiaEdu & Lead DevOps Engineer

⚡ Executive Summary

A practical operational guide covering RAG metrics (Context Precision, Recall, Groundedness) and physical serving metrics (TTFT, VRAM sizing, Throughput).

Key Takeaways

  • RAG-Specific Metrics (RAGAS / TruLens) — covered in depth with practical examples, formulas, and code.
  • Deployment & Inference Serving Metrics — covered in depth with practical examples, formulas, and code.

RAG Evaluation & Production Serving Metrics


#1. RAG-Specific Metrics (RAGAS / TruLens)

MetricEvaluatesFailure mode caught
Context PrecisionRetrieverNoise / irrelevant retrieved chunks
Context RecallRetrieverMissing necessary information
GroundednessGeneratorModel hallucinating beyond context
Answer RelevancyGeneratorAnswering a different question
python
from ragas import evaluate
from ragas.metrics import context_precision, context_recall, faithfulness, answer_relevancy

results = evaluate(dataset, metrics=[context_precision, context_recall, faithfulness, answer_relevancy])

#2. Deployment & Inference Serving Metrics

2.1 TTFT — Time To First Token

Latency from request start to token #1 output. Measures user-perceived responsiveness.

2.2 Tokens/sec & Latency

Rate of output token generation during decode phase. p50/p90/p99 latency percentiles.

2.3 Throughput

Total tokens processed per unit time across concurrent requests:

MATHEMATICAL FORMULA Throughput = (total tokens across all requests) / (time)

2.4 VRAM Sizing Formula

GPU memory footprint for model weights:

MATHEMATICAL FORMULA VRAM Weight Size ≈ Parameters × Bytes per Parameter

  • FP32: 4 bytes/param
  • FP16/BF16: 2 bytes/param (7B model ≈ 14 GB)
  • INT8: 1 byte/param (7B model ≈ 7 GB)
  • INT4: 0.5 bytes/param (7B model ≈ 3.5 GB)
  • Tags:#RAG Metrics#TTFT#Tokens/sec#Latency#Throughput#VRAM#DevOps
    ABOUT THE AUTHOR
    YP

    Yashika P

    Founder @ AscendiaEdu & Lead DevOps Engineer

    Yashika P is part of the Junglans Solutions engineering team, specializing in llm evaluation & benchmarking. Junglans builds a 20-product ecosystem of local-first enterprise software — AI developer tools, encrypted communication, and data infrastructure with zero cloud telemetry.

    Meet the full Junglans engineering team ↗
    RELATED RESOURCES & REFERENCES

    This article is part of the Junglans Research knowledge base, produced alongside the engineering teams that build our production AI tools. Explore related product documentation and research:

    Related Research & Articles