# GGUF File Size by Quantisation Level

> Work out the download size of a quantised model at every GGUF level, and what quality each one costs you.

A GGUF file is parameters × effective bits per weight ÷ 8. The effective figure is higher than the nominal one because each block of weights carries its own scale — Q4_K_M is 4.83 bits per weight, not 4 — so an 8B model at Q4_K_M is about 4.5 GB rather than 4. This calculator gives the size at all eight common levels with what each costs in quality.

**URL:** https://convertto.tech/t/gguf-size-calculator
**Category:** AI & LLM Tools (https://convertto.tech/c/ai-tools)
**Privacy:** Runs entirely in the browser; no upload
**Cost:** Free, no sign-up
**Last updated:** 2026-08-01

## Key facts

- **Privacy:** Runs entirely in your browser — nothing is uploaded
- **Cost:** Free, unlimited, no sign-up

## How to use

1. Set the parameters.
2. Choose the quantisation.
3. Turn "Show every level" on or off as needed.
4. The result appears immediately — copy or download it.

## FAQ

### Which quantisation should I download?

Q4_K_M unless you have memory to spare, in which case Q5_K_M or Q6_K. Below Q3 the loss on reasoning and code becomes obvious, and Q2 is rarely worth it — a smaller model at Q4 will usually serve you better.

### Why is Q4_K_M bigger than Q4_0 if both are 4-bit?

Because K-quants keep the tensors that matter most — attention and parts of the feed-forward network — at a higher precision than the rest, and carry more per-block metadata. The extra few hundred megabytes buy a measurable quality improvement, which is why Q4_K_M is the community default.

## Sources

- [llama.cpp — GGUF specification](https://github.com/ggml-org/ggml/blob/master/docs/gguf.md) — ggml

## Related tools

- [LLM VRAM Calculator](https://convertto.tech/t/llm-vram-calculator): Work out exactly how much video memory a local model needs, including the KV cache that scales with context length.
- [Base64 to File Converter](https://convertto.tech/t/base64-to-file): Decode Base64, a data URI or hex back into a downloadable file, with the type detected automatically.
- [Paste Image and Download](https://convertto.tech/t/paste-image-to-png): Press Ctrl+V to paste a screenshot or copied image, then download it as a real file. Nothing is uploaded.
- [Sample File Library](https://convertto.tech/t/sample-file-library): Download a ready-made ladder of 15 sample files: size steps, page counts, aspect ratios, durations or row counts.
- [AI API Cost Calculator](https://convertto.tech/t/ai-api-cost-calculator): Work out what a prompt costs per call, per day and per month, and compare the same workload across every major model.
- [AI Writing Pattern Checker](https://convertto.tech/t/ai-writing-pattern-checker): Measure sentence-length variance, vocabulary richness, marker phrases and typographic tells, with per-sentence scoring.
- [Chat Export Formatter](https://convertto.tech/t/chat-export-formatter): Drop in an exported conversations file and get clean Markdown, HTML or plain text — one document per conversation.
- [Context Window Calculator](https://convertto.tech/t/context-window-calculator): Paste a document and see which models it fits inside, how much of each window it fills, and what is left for the reply.