# LLaMA-Factory

- **Canonical URI:** https://www.vioscale.ai/software/llama-factory
- **Category:** Fine Tuning Platforms
- **Homepage:** https://llamafactory.readthedocs.io
- **Also known as:** llama-factory
- **Profile claimed by vendor:** no
- **Last updated:** 2026-08-26T19:58:08.397Z

## Vioscale score

**59.2 / 100**, confidence 24% (low). Computed 2026-09-01. _(updating — computed under an earlier model version or past its freshness window.)_

Composite of weighted, independently-sourced signals (no user reviews, no vendor payment).

| Signal | Score | Weight | Contribution | Evidence present |
|---|--:|--:|--:|:--:|
| capabilities | 86.7 | 0.07844444444444446 | 6.8 | ✓ |
| repo_stars | 91.9 | 0.026 | 2.4 | ✓ |
| integrations | 26 | 0.07033333333333334 | 1.8 | ✓ |
| dependent_projects | 0 | 0.063 | 0 | - |
| dev_activity | 37 | 0.094 | 3.5 | ✓ |
| release_cadence | 86.1 | 0.052 | 4.5 | ✓ |
| security_posture | 0 | 0.073 | 0 | - |
| package_downloads | 0 | 0.136 | 0 | - |
| security_score | 0 | 0.042 | 0 | - |
| community_qa_activity | 0 | 0.063 | 0 | - |

## Pricing

_As of 2026-08-21, [verify at source](https://llamafactory.readthedocs.io). Independently observed._

Open source

> Free and open source

## About

LlamaFactory is a user-friendly training and fine-tuning platform that enables local optimization of hundreds of pre-trained language models without requiring code. It supports diverse training methods including supervised fine-tuning, reinforcement learning approaches, and parameter-efficient techniques.

_Independently observed._

## Platform & deployment

- **Platforms:** CLI
- **Deployment:** Self-hosted

## Integrations (7)

_Independently observed._

- TensorBoard
- Wandb
- MLflow
- SwanLab
- Transformers
- vLLM
- Hugging Face Hub

## Capabilities

_The capabilities that matter for Fine Tuning Platforms. "-" = undocumented, not absent._

| Capability | Supported |
|---|:--:|
| **Capabilities** | |
| Architecture model | Open source library local GPU |
| Peft lora and qlora parameter efficient tuning | ✓ |
| Rlhf and dpo preference alignment optimization | ✓ |
| Serverless hosting of fine tuned adapters lorax | - |
| Four bit and eight bit memory quantization | ✓ |
| Flash attention and xformers compilation | ✓ |
| Distributed multi GPU orchestration fsdp deepspeed | ✓ |
| Synthetic data generation and evaluation pipeline | - |
| Native huggingface hub push pull integration | - |
| Weights and biases wandb experiment tracking | ✓ |
| SOC2 type ii | - |
| Mit or apache permissive oss license | ✓ |
| Pricing model | Free open source |

## Release history

| Version | Date | Type |
|---|---|---|
| [v0.9.5](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.5) | 2026-05-30 | stable |
| [v0.9.4](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.4) | 2025-12-31 | stable |
| [v0.9.3](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.3) | 2025-06-16 | stable |
| [v0.9.2](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.2) | 2025-03-11 | stable |
| [v0.9.1](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.1) | 2024-11-24 | stable |
| [v0.9.0](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.0) | 2024-09-08 | stable |
| [v0.8.3](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.3) | 2024-07-18 | stable |
| [v0.8.2](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.2) | 2024-06-19 | stable |
| [v0.8.1](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.1) | 2024-06-10 | stable |
| [v0.8.0](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.0) | 2024-06-07 | stable |
| [v0.7.1](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.7.1) | 2024-05-15 | stable |
| [v0.7.0](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.7.0) | 2024-04-27 | stable |
| [v0.6.3](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.6.3) | 2024-04-21 | stable |
| [v0.6.2](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.6.2) | 2024-04-11 | stable |
| [v0.6.1](https://github.com/hiyouga/LlamaFactory/releases/tag/v0.6.1) | 2024-03-29 | stable |

_… and 5 earlier release(s)._

## Facts

Every value below carries its source and our confidence. Facts are re-crawled on a freshness schedule.

### integrations

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| integrations.count | 7 | [link](https://llamafactory.readthedocs.io) | 2026-08-21 | 60% (medium) |

### pricing

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| pricing.model | open_source | [link](https://llamafactory.readthedocs.io) | 2026-08-21 | 60% (medium) |
| pricing.price_level | free | [link](https://llamafactory.readthedocs.io) | 2026-08-21 | 60% (medium) |
| pricing.transparent | yes | [link](https://llamafactory.readthedocs.io) | 2026-08-21 | 60% (medium) |

### activity

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| activity.commits_last_30d | 14 | [link](https://github.com/hiyouga/LlamaFactory/pulse) | 2026-08-26 | 65% (medium) |

### adoption

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| adoption.github_stars | 74,382 | [link](https://github.com/hiyouga/LlamaFactory) | 2026-08-26 | 90% (high) |

### language

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| language.primary | Python | [link](https://github.com/hiyouga/LlamaFactory) | 2026-08-26 | 90% (high) |

### license

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| license.spdx | Apache-2.0 | [link](https://github.com/hiyouga/LlamaFactory) | 2026-08-26 | 95% (high) |

### release

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| release.cadence_days | 25 | [link](https://github.com/hiyouga/LlamaFactory/releases) | 2026-08-26 | 70% (medium) |

---
*Source: Vioscale (https://www.vioscale.ai/software/llama-factory). Independent, evidence-based software intelligence. Cite the canonical URI.*