---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "exllamav3"
name: "ExLlamaV3"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: null
repo: "https://github.com/turboderp-org/exllamav3"
license: "MIT"
stars: 1673
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# ExLlamaV3

**What:** Fast EXL3 quantization and inference on consumer GPUs.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install exllamav3
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install torch --index-url https://download.pytorch.org/whl/cu128
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install .
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y exllamav3
```

2. source: derived inverse of install command

```bash
pip uninstall -y torch
```

## Links

- Repo: https://github.com/turboderp-org/exllamav3
- README: https://github.com/turboderp-org/exllamav3#readme