# LLaMA-Factory vs Unsloth

| Attribute | LLaMA-Factory | Unsloth |
|---|---|---|
| **Vioscale score** | 59.2 (24% (low)) | 54.9 (40% (low)) |
| activity.commits_last_30d | 14 | 100 |
| adoption.dependent_repos | - | 0 |
| adoption.github_stars | 74,382 | 74,869 |
| deployment.options | `{"self_hosted":true}` | `{"cloud":true,"self_hosted":true}` |
| description.long | 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. | Unsloth is a free, open-source desktop app that lets users run, customize, and train AI models on their own hardware with optimizations for speed and memory usage. It supports multiple GPU setups and offers paid Pro and Enterprise tiers with enhanced performance and deployment capabilities. |
| features.capabilities | `{"pricing_model":"free_open_source","architecture_model":"open_source_library_local_gpu","mit_or_apache_permissive_oss_license":true,"flash_attention_and_xformers_compilation":true,"four_bit_and_eight_bit_memory_quantization":true,"weights_and_biases_wandb_experiment_tracking":true,"peft_lora_and_qlora_parameter_efficient_tuning":true,"rlhf_and_dpo_preference_alignment_optimization":true,"distributed_multi_gpu_orchestration_fsdp_deepspeed":true}` | `{"pricing_model":"free_open_source","architecture_model":"open_source_library_local_gpu","mit_or_apache_permissive_oss_license":true,"flash_attention_and_xformers_compilation":true,"four_bit_and_eight_bit_memory_quantization":true,"native_huggingface_hub_push_pull_integration":true,"peft_lora_and_qlora_parameter_efficient_tuning":true,"rlhf_and_dpo_preference_alignment_optimization":true,"distributed_multi_gpu_orchestration_fsdp_deepspeed":true}` |
| integrations.count | 7 | 18 |
| integrations.list | `[{"name":"TensorBoard"},{"name":"Wandb"},{"name":"MLflow"},{"name":"SwanLab"},{"name":"Transformers"},{"name":"vLLM"},{"name":"Hugging Face Hub"}]` | `[{"name":"Claude Code"},{"name":"Codex"},{"name":"OpenAI API"},{"name":"Hugging Face"},{"name":"Google"},{"name":"Model Context Protocol"},{"name":"Cloudflare"},{"name":"FLUX"},{"name":"MiniMax-H3"},{"name":"Stable Diffusion"},{"name":"Qwen3.8"},{"name":"DeepSeek-V4"},{"name":"Gemma 2"},{"name":"Gemma 4"},{"name":"Mistral"},{"name":"Llama 1"},{"name":"Llama 2"},{"name":"Llama 3"}]` |
| language.primary | Python | Python |
| license.spdx | Apache-2.0 | Apache-2.0 |
| platform.support | `{"cli":true}` | `{"mac":true,"web":true,"linux":true,"windows":true}` |
| pricing | `{"type":"open_source","summary":"Free and open source","sourceUrl":"https://llamafactory.readthedocs.io","retrievedAt":"2026-08-21T11:03:55.421Z"}` | `{"type":"hybrid","plans":[{"free":true,"name":"Free","summary":"Free, open-source","features":["Supports Mistral, Gemma, Llama 1/2/3 models","4-bit and 16-bit LoRA fine-tuning","Single GPU support","2x speed improvement","60% VRAM reduction","Fully local and offline operation"],"components":[{"kind":"fixed","amount":0,"period":"month","currency":"USD"}],"description":"Open-source version with core model training capabilities","contactSales":false},{"free":false,"name":"Pro","summary":"Contact sales for pricing","features":["2.5x faster training","20% less VRAM usage","Multi-GPU support up to 8 GPUs","80% VRAM reduction","Support for any use case"],"description":"Enhanced performance with multi-GPU support","contactSales":true},{"free":false,"name":"Enterprise","summary":"Contact sales for pricing","features":["30x faster training","Up to 30% accuracy improvement","5x faster inference","Multi-node support","90% VRAM reduction","Full training support","Customer support included"],"description":"Maximum performance with multi-node deployment and accuracy improvements","contactSales":true}],"summary":"Free open-source tier; Pro and Enterprise plans available","freeTier":true,"sourceUrl":"https://unsloth.ai/pricing","retrievedAt":"2026-08-21T11:04:21.735Z"}` |
| pricing.free_tier | - | yes |
| pricing.model | open_source | freemium |
| pricing.price_level | free | low |
| pricing.transparent | yes | no |
| release.cadence_days | 25 | 4 |
| release.history | `[{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.5","date":"2026-05-30T15:57:58Z","type":"stable","version":"v0.9.5"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.4","date":"2025-12-31T15:00:14Z","type":"stable","version":"v0.9.4"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.3","date":"2025-06-16T17:21:46Z","type":"stable","version":"v0.9.3"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.2","date":"2025-03-11T13:47:35Z","type":"stable","version":"v0.9.2"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.1","date":"2024-11-24T17:17:33Z","type":"stable","version":"v0.9.1"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.9.0","date":"2024-09-08T17:14:03Z","type":"stable","version":"v0.9.0"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.3","date":"2024-07-18T18:00:06Z","type":"stable","version":"v0.8.3"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.2","date":"2024-06-19T13:06:16Z","type":"stable","version":"v0.8.2"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.1","date":"2024-06-10T16:50:22Z","type":"stable","version":"v0.8.1"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.8.0","date":"2024-06-07T22:26:46Z","type":"stable","version":"v0.8.0"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.7.1","date":"2024-05-15T18:16:30Z","type":"stable","version":"v0.7.1"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.7.0","date":"2024-04-27T20:24:50Z","type":"stable","version":"v0.7.0"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.6.3","date":"2024-04-21T15:43:07Z","type":"stable","version":"v0.6.3"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.6.2","date":"2024-04-11T12:27:01Z","type":"stable","version":"v0.6.2"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.6.1","date":"2024-03-29T04:07:57Z","type":"stable","version":"v0.6.1"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.6.0","date":"2024-03-25T15:50:44Z","type":"stable","version":"v0.6.0"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.5.3","date":"2024-02-28T17:01:31Z","type":"stable","version":"v0.5.3"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.5.2","date":"2024-02-20T07:32:43Z","type":"stable","version":"v0.5.2"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.5.0","date":"2024-01-20T18:37:07Z","type":"stable","version":"v0.5.0"},{"url":"https://github.com/hiyouga/LlamaFactory/releases/tag/v0.4.0","date":"2023-12-16T13:48:38Z","type":"stable","version":"v0.4.0"}]` | `[{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.803-beta","date":"2026-08-25T13:12:45Z","type":"stable","version":"v0.1.803-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.802-beta","date":"2026-08-25T11:27:29Z","type":"stable","version":"v0.1.802-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.801-beta","date":"2026-08-20T16:58:37Z","type":"stable","version":"v0.1.801-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.800-beta","date":"2026-08-14T14:18:49Z","type":"stable","version":"v0.1.800-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.702-beta","date":"2026-08-13T15:21:18Z","type":"stable","version":"v0.1.702-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.701-beta","date":"2026-08-11T19:24:35Z","type":"stable","version":"v0.1.701-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.70-beta","date":"2026-08-11T15:31:25Z","type":"stable","version":"v0.1.70-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.62-beta","date":"2026-08-11T13:25:36Z","type":"stable","version":"v0.1.62-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.61-beta","date":"2026-08-10T13:57:15Z","type":"stable","version":"v0.1.61-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.60-beta","date":"2026-08-10T11:59:46Z","type":"stable","version":"v0.1.60-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.527-beta","date":"2026-08-09T17:14:42Z","type":"stable","version":"v0.1.527-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.526-beta","date":"2026-08-04T16:06:43Z","type":"stable","version":"v0.1.526-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.512-beta","date":"2026-07-29T15:35:36Z","type":"stable","version":"v0.1.512-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.501-beta","date":"2026-07-20T14:06:46Z","type":"stable","version":"v0.1.501-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.49-beta","date":"2026-07-15T18:27:06Z","type":"stable","version":"v0.1.49-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.481-beta","date":"2026-07-07T14:43:29Z","type":"stable","version":"v0.1.481-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.471-beta","date":"2026-06-18T17:36:51Z","type":"stable","version":"v0.1.471-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.464-beta","date":"2026-06-12T13:57:31Z","type":"stable","version":"v0.1.464-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.451-beta","date":"2026-06-10T18:20:29Z","type":"stable","version":"v0.1.451-beta"},{"url":"https://github.com/unslothai/unsloth/releases/tag/v0.1.44-beta","date":"2026-06-03T14:35:44Z","type":"stable","version":"v0.1.44-beta"}]` |
| security.scorecard | - | 4.9 |
| security.vulnerabilities | - | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=roland-sloth&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (Fine Tuning Platforms)

| Capability | LLaMA-Factory | Unsloth |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Architecture model | Open source library local GPU | 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 | Free open source |

*Source: Vioscale. Generated 2026-09-01T14:46:54.937Z. "-" = undocumented, not absent.*