---
title: "Community Benchmarks & Quant Guides — Catalog"
type: summary
tags: [catalog, benchmarks, quantization, community]
updated: 2026-06-09
confidence: medium
sources: [raw/community/community-bench-apple-silicon.md, raw/community/community-bench-nvidia-cuda.md, raw/community/community-dgxspark-kv-quant.md, raw/community/community-bartowski-quant-guide.md, raw/community/community-kaitchup-gguf-guide.md, raw/community/community-steelphoenix-guide.md, raw/community/community-unsloth-dynamic-ggufs.md, raw/community/community-mradermacher-imatrix.md, raw/community/community-artefact2-quant-table.md, raw/community/community-arxiv-quant-eval.md, raw/community/community-pr1684-kquants.md, raw/community/community-smcleod-kv-quant.md, raw/community/community-gh15180-vllm-vs-llamacpp.md, raw/community/community-redhat-vllm-vs-llamacpp.md, raw/community/community-hf-gguf-usage.md]
---

# Community Benchmarks & Quant Guides — Catalog

Map of the 15 provenance-stamped community sources in `raw/community/` (each carries its source URL + author). Use this to answer "is there data on X?" — details live in the cited files and the synthesis pages.

## Hardware benchmarks

- **Apple Silicon** performance discussion (llama.cpp GitHub discussions)
- **NVIDIA CUDA** benchmarks
- **DGX Spark KV-cache quantization** measurements

## Quantization guides & evaluations

- **bartowski's quant guide** (HF model-card conventions — the de-facto community quant naming)
- **Kaitchup GGUF guide** · **SteelPhoenix guide** · **HF GGUF usage docs**
- **Unsloth dynamic GGUFs** (dynamic quantization approach)
- **mradermacher imatrix** practices
- **artefact2 quant comparison table** · **arXiv quant evaluation** (academic eval) · **PR #1684** (the original k-quants design)

## KV-cache quantization

- **smcleod KV-quant guide** + the DGX Spark measurements above

## Engine comparisons

- **vLLM vs llama.cpp**: GitHub issue #15180 thread + Red Hat's comparison ([[syntheses/llamacpp-vs-vllm]] synthesizes these)

Related: [[syntheses/quant-types-compared]] · [[concepts/cli-and-tools-reference]] (llama-bench).
