{ "data": { "a": { "slug": "axolotl", "name": "Axolotl", "vendor": "Axolotl AI", "vendorUrl": "https://axolotl.ai", "kind": "framework", "category": "fine-tuning", "summary": "Open-source command-line tool and Python package for fine-tuning open language models from one YAML config, covering LoRA, QLoRA, full fine-tuning, preference tuning and GRPO on the owner's GPUs.", "url": "https://www.anchorterminal.com/tools/axolotl", "markdownUrl": "https://www.anchorterminal.com/tools/axolotl.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/axolotl.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/axolotl.json", "repo": "https://github.com/axolotl-ai-cloud/axolotl", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "axolotl" }, { "registry": "oci", "name": "axolotlai/axolotl" } ], "auth": "none", "authNotes": "No account or key of its own. Gated models and Hub uploads use the owner's Hugging Face token, and Weights \u0026 Biases, MLflow or Trackio logging uses those services' own credentials from the environment.", "pricing": "free", "pricingNotes": "Free and Apache-2.0, with no price list or hosted plan on axolotl.ai. The owner pays for the GPU, whether local, a rented machine or Hugging Face Jobs billed by the minute. Dedicated support is by email with no published price.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 12541, "npmWeekly": null, "pypiWeekly": 2124, "asOf": "2026-10-08" }, "docsUrl": "https://docs.axolotl.ai/", "capabilities": [ "finetune.sft", "finetune.lora", "finetune.preference", "finetune.rl", "finetune.export" ], "tags": [ "open-source", "framework", "self-hosted", "local", "free", "python", "docker", "open-weights" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 64.8, "grade": "B", "agentReady": false, "rank": 307, "ranked": true, "rankOf": 842, "categoryRank": 2, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 88, "payments": 60, "reliability": 64, "schema": 80, "security": 52, "transparency": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Axolotl runs a whole fine-tuning job from one YAML file and ships a JSON Schema of its config plus bundled agent docs. It is 0.x software with telemetry on by default, no terms or privacy policy, and the owner supplies the GPU.", "bestFor": "A team that wants a repeatable, config-driven fine-tune of an open model on its own or rented GPUs, including multi-GPU and multi-node runs.", "strengths": [ "Apache-2.0, free, and the weights stay on the owner's hardware", "`axolotl config-schema` prints the full config as JSON Schema, and `axolotl agent-docs` prints bundled Markdown references by topic", "SFT, LoRA, QLoRA, DPO, IPO, KTO, ORPO, GRPO and reward modelling from one config format", "Three releases in the 90 days to 8 October 2026, each with a Deprecations section naming removed options", "Telemetry is documented field by field and `AXOLOTL_DO_NOT_TRACK=1` turns it off" ], "weaknesses": [ "Telemetry to PostHog is on by default and delays training start by 10 seconds until the variable is set either way", "No terms of service, privacy policy, legal entity or security.txt found on axolotl.ai", "Version 0.20.0, with removals in minor releases (FSDP1 in 0.20.0, `relora_steps` renamed in 0.17.0 with no shim)", "Three of the last six push runs of the Tests workflow on main passed, and the nightly run against upstream failed on 7 and 8 October 2026", "Not a hosted service, so there is no job API, status page or SLA" ], "agentNotes": [ "Set `AXOLOTL_DO_NOT_TRACK=1` before any command, or training waits 10 seconds and sends usage events to PostHog", "Run `axolotl agent-docs` and `axolotl config-schema --field \u003cname\u003e` before writing a config; both work offline from the installed package", "Install torch first, then `uv pip install --no-build-isolation axolotl[deepspeed]`, on Python 3.12 or later with PyTorch 2.13 or later", "Take example configs from the same release tag as the installed version; minor releases remove and rename config keys", "Resume an interrupted run with `axolotl train config.yml --resume-from-checkpoint \u003cpath\u003e`, then `axolotl merge-lora` and `axolotl export` only when shipping" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.8 } ], "editorialScores": { "ergonomics": 60, "maintenance": 88, "payments": 60, "reliability": 64, "schema": 80, "security": 52, "transparency": 75 }, "provenanceScore": 36 }, "connect": { "install": "uv pip install torch==2.14.0 torchvision \u0026\u0026 uv pip install --no-build-isolation axolotl[deepspeed] # or: docker run --gpus '\"all\"' --ipc=host --rm -it axolotlai/axolotl:main-latest", "headless": { "command": "axolotl train config.yml", "env": { "AXOLOTL_DO_NOT_TRACK": "1" } } }, "letme": { "capability": "https://letme.dev/finetune.sft", "tool": "https://letme.dev/axolotl" }, "area": "models", "provenance": { "legalEntity": "", "domain": "axolotl.ai", "domainRegistered": "2022-08-02", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/axolotl-ai-cloud/axolotl/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "No legal entity is named on axolotl.ai, in the docs or in the repository. The GitHub organisation is axolotl-ai-cloud and the citation file credits the Axolotl maintainers and contributors.", "The vendor publishes no terms of service or privacy policy (axolotl.ai/terms and /privacy return 404), so both links are left out. The telemetry page is the only data-handling statement.", "Local software has no endpoint to check against the domain.", "axolotl.ai/.well-known/security.txt and /security.txt return 404. The repository's `.github/SECURITY.md` gives an email address for reports.", "RDAP shows axolotl.ai registered on 2 August 2022 and transferred on 11 April 2024." ], "score": 36 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/axolotl.json" }, "answer": "Axolotl scores 64.8 (B) on agent readiness against Unsloth's 51.5 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "unsloth", "name": "Unsloth", "vendor": "Unsloth", "vendorUrl": "https://unsloth.ai", "kind": "framework", "category": "fine-tuning", "summary": "Open-source library, web UI (Studio) and desktop app for LoRA, QLoRA, full fine-tuning and RL (GRPO, DPO, ORPO) of open models on your own GPU, from 3 GB of VRAM.", "url": "https://www.anchorterminal.com/tools/unsloth", "markdownUrl": "https://www.anchorterminal.com/tools/unsloth.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/unsloth.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/unsloth.json", "repo": "https://github.com/unslothai/unsloth", "license": "Apache-2.0 (core), AGPL-3.0 (Studio UI)", "transports": [], "packages": [ { "registry": "pypi", "name": "unsloth" } ], "auth": "none", "authNotes": "No account. Studio asks for an admin password when exposed beyond loopback (`--secure`, `--cloudflare` or a non-loopback host), and hands out API keys for its OpenAI-compatible server under Settings.", "pricing": "free", "pricingNotes": "Free and open source. You pay for the GPU it runs on, whether a free Colab or Kaggle notebook, your own card or a rented one. Docker images `unsloth/unsloth` and `unsloth/unsloth-rocm` on Docker Hub. No hosted plan or price list appears on the site or in the docs index (https://unsloth.ai/docs).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 76900, "npmWeekly": null, "pypiWeekly": 230075, "asOf": "2026-09-30" }, "docsUrl": "https://unsloth.ai/docs", "llmsTxt": "https://unsloth.ai/docs/llms.txt", "capabilities": [ "finetune.sft", "finetune.preference", "finetune.rl", "finetune.lora", "finetune.export" ], "tags": [ "open-source", "framework", "self-hosted", "local", "free", "python", "llms-txt", "open-weights" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 51.5, "grade": "D", "agentReady": false, "rank": 668, "ranked": true, "rankOf": 842, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 53, "maintenance": 82, "payments": 60, "reliability": 43, "schema": 66, "security": 35, "transparency": 32 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "The Apache-2.0 core runs on customer hardware and keeps model weights there. Users supply and pay for the GPU.", "bestFor": "One person or a small team tuning an open model on their own GPU and keeping the weights.", "strengths": [ "Free and open source, Apache-2.0 core, with the weights staying on your hardware", "LoRA, QLoRA, full fine-tuning, GRPO, DPO and ORPO from one package", "Exports adapters, merged 16-bit weights and GGUF for vLLM, Ollama or llama.cpp", "Fifteen PyPI releases between 25 August and 28 September 2026", "llms.txt and over 100 model-specific notebooks" ], "weaknesses": [ "Not a hosted service; you bring and pay for the GPU", "Studio is AGPL-3.0, and its server-side tools are on by default when exposed", "792 open issues and 472 open pull requests", "No legal entity in the terms, no privacy page and no security.txt", "Calendar versions with no breaking-change notes and no deprecation policy" ], "agentNotes": [ "Install with `uv pip install unsloth --torch-backend=auto` on a CUDA machine; the desktop app is for people", "Start from the notebook for the model family in unslothai/notebooks; it sets LoRA targets and the chat template", "Save the LoRA adapter while iterating and merge to 16-bit or GGUF only when you ship", "If Studio must be reachable by other agents, pass --disable-tools and keep it on 127.0.0.1 behind a tunnel", "Pin the exact unsloth version; releases land several times a week and don't flag breaking changes" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.5 } ], "editorialScores": { "ergonomics": 53, "maintenance": 82, "payments": 60, "reliability": 43, "schema": 66, "security": 35, "transparency": 40 }, "provenanceScore": 23 }, "connect": { "install": "curl -fsSL https://unsloth.ai/install.sh | sh # or: uv pip install unsloth --torch-backend=auto" }, "letme": { "capability": "https://letme.dev/finetune.sft", "tool": "https://letme.dev/unsloth" }, "area": "models", "provenance": { "legalEntity": "", "domain": "unsloth.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://unsloth.ai/terms", "privacy": "", "statusPage": "", "changelog": "https://github.com/unslothai/unsloth/releases", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The terms page names no company, address or date, and unsloth.ai/privacy returns 404. Copyright notices in the source credit Daniel Han-Chen and the Unsloth team.", "A local library has no endpoint to check against the domain.", "unsloth.ai/.well-known/security.txt returns 404.", "The .ai registry's RDAP server refused our requests, so the registration date is blank.", "lastRelease is blank because releases are versioned by date (2026.9.12) and we didn't confirm the tag date; the last commit was 2026-09-30." ], "score": 23 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/unsloth.json", "live": { "slug": "unsloth", "versions": [ { "registry": "github", "name": "unslothai/unsloth", "version": "v0.1.905-beta", "released": "2026-10-08", "seenAt": "2026-10-08T16:33:23.101894009Z" }, { "registry": "pypi", "name": "unsloth", "version": "2026.10.3", "released": "2026-10-08", "seenAt": "2026-10-08T16:33:22.984821349Z" } ], "githubStars": 77487, "pypiWeekly": 177890, "securityTxt": { "url": "https://unsloth.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:59.33731935Z" }, "llmsTxt": { "url": "https://unsloth.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:57.572131254Z" }, "domain": { "domain": "unsloth.ai", "registered": "2023-11-27", "source": "https://rdap.identitydigital.services/rdap/domain/unsloth.ai", "checkedAt": "2026-10-04T13:08:02.898044488Z" }, "pages": [ { "url": "https://unsloth.ai/terms", "kind": "terms", "status": 404, "checkedAt": "2026-10-08T18:25:27.328582164Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-08T18:25:27.328582164Z" } }, "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Axolotl AI", "b": "Unsloth", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0 (core), AGPL-3.0 (Studio UI)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-30", "b": "2026-09-28", "name": "Last release" }, { "a": "no document linked", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "13k stars, 2.1k PyPI/wk", "b": "77k stars, 230k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Axolotl scores 64.8 (B) on agent readiness against Unsloth's 51.5 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Axolotl or Unsloth?" }, { "answer": "Yes. Axolotl is open source (Apache-2.0). Unsloth is open source (Apache-2.0 (core), AGPL-3.0 (Studio UI)).", "question": "Are Axolotl and Unsloth open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 64 against 43", "Schema \u0026 documentation, 80 against 66", "Agent ergonomics, 60 against 53", "Security \u0026 auth, 52 against 35", "Maintenance \u0026 community, 88 against 82", "Transparency \u0026 trust, 56 against 32" ], "also": null, "goodFor": "A team that wants a repeatable, config-driven fine-tune of an open model on its own or rented GPUs, including multi-GPU and multi-node runs.", "slug": "axolotl", "watchFor": "Telemetry to PostHog is on by default and delays training start by 10 seconds until the variable is set either way" }, { "aheadOn": null, "also": null, "goodFor": "One person or a small team tuning an open model on their own GPU and keeping the weights.", "slug": "unsloth", "watchFor": "Not a hosted service; you bring and pay for the GPU" } ], "job": { "capability": "finetune.sft", "name": "Finetune sft" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-axolotl.json", "title": "Amazon Bedrock model customisation vs Axolotl", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-axolotl" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-unsloth.json", "title": "Amazon Bedrock model customisation vs Unsloth", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-azure-foundry-fine-tuning.json", "title": "Axolotl vs Microsoft Foundry fine-tuning (Azure OpenAI)", "url": "https://www.anchorterminal.com/compare/axolotl-vs-azure-foundry-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-fireworks-fine-tuning.json", "title": "Axolotl vs Fireworks AI Fine-tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-fireworks-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-nebius-token-factory-fine-tuning.json", "title": "Axolotl vs Nebius Token Factory fine-tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-nebius-token-factory-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-tinker.json", "title": "Axolotl vs Tinker", "url": "https://www.anchorterminal.com/compare/axolotl-vs-tinker" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-together-fine-tuning.json", "title": "Axolotl vs Together AI Fine-tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-together-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-vertex-ai-tuning.json", "title": "Axolotl vs Vertex AI Gemini tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-vertex-ai-tuning" }, { "json": "https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-unsloth.json", "title": "Microsoft Foundry fine-tuning (Azure OpenAI) vs Unsloth", "url": "https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-unsloth.json", "title": "Fireworks AI Fine-tuning vs Unsloth", "url": "https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-unsloth.json", "title": "Nebius Token Factory fine-tuning vs Unsloth", "url": "https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/tinker-vs-unsloth.json", "title": "Tinker vs Unsloth", "url": "https://www.anchorterminal.com/compare/tinker-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/together-fine-tuning-vs-unsloth.json", "title": "Together AI Fine-tuning vs Unsloth", "url": "https://www.anchorterminal.com/compare/together-fine-tuning-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/unsloth-vs-vertex-ai-tuning.json", "title": "Unsloth vs Vertex AI Gemini tuning", "url": "https://www.anchorterminal.com/compare/unsloth-vs-vertex-ai-tuning" } ], "scores": [ { "axolotl": 64, "by": 21, "edge": "axolotl", "key": "reliability", "name": "Reliability", "unsloth": 43, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "axolotl": 80, "by": 14, "edge": "axolotl", "key": "schema", "name": "Schema \u0026 documentation", "unsloth": 66, "weight": 13 }, { "axolotl": 60, "by": 7, "edge": "axolotl", "key": "ergonomics", "name": "Agent ergonomics", "unsloth": 53, "weight": 13 }, { "axolotl": 52, "by": 17, "edge": "axolotl", "key": "security", "name": "Security \u0026 auth", "unsloth": 35, "weight": 14 }, { "axolotl": 60, "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "unsloth": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "axolotl": 88, "by": 6, "edge": "axolotl", "key": "maintenance", "name": "Maintenance \u0026 community", "unsloth": 82, "weight": 7 }, { "axolotl": 56, "by": 24, "edge": "axolotl", "key": "transparency", "name": "Transparency \u0026 trust", "unsloth": 32, "weight": 7 } ], "summary": "Axolotl scores 64.8 (B) on agent readiness against Unsloth's 51.5 (D), and leads in 6 of 7 scored categories. Both do finetune sft.", "verdicts": { "axolotl": "Axolotl runs a whole fine-tuning job from one YAML file and ships a JSON Schema of its config plus bundled agent docs. It is 0.x software with telemetry on by default, no terms or privacy policy, and the owner supplies the GPU.", "unsloth": "The Apache-2.0 core runs on customer hardware and keeps model weights there. Users supply and pay for the GPU." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/axolotl-vs-unsloth", "json": "https://www.anchorterminal.com/compare/axolotl-vs-unsloth.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/axolotl-vs-unsloth.md", "slim": "https://www.anchorterminal.com/compare/axolotl-vs-unsloth.min.md" }, "markdown": "Axolotl scores 64.8 (B) on agent readiness against Unsloth's 51.5 (D), and leads in 6 of 7 scored categories. Both do finetune sft.\n\n- Axolotl: grade B, 64.8/100, rank #307 of 842. Markdown https://www.anchorterminal.com/tools/axolotl.md · JSON https://www.anchorterminal.com/api/v1/tools/axolotl.json\n- Unsloth: grade D, 51.5/100, rank #668 of 842. Markdown https://www.anchorterminal.com/tools/unsloth.md · JSON https://www.anchorterminal.com/api/v1/tools/unsloth.json\n\n## Which one, for what\n\n### Axolotl (B)\n\nGood for: A team that wants a repeatable, config-driven fine-tune of an open model on its own or rented GPUs, including multi-GPU and multi-node runs.\n\nAhead on:\n- Reliability, 64 against 43\n- Schema \u0026 documentation, 80 against 66\n- Agent ergonomics, 60 against 53\n- Security \u0026 auth, 52 against 35\n- Maintenance \u0026 community, 88 against 82\n- Transparency \u0026 trust, 56 against 32\n\nWatch for: Telemetry to PostHog is on by default and delays training start by 10 seconds until the variable is set either way\n\n### Unsloth (D)\n\nGood for: One person or a small team tuning an open model on their own GPU and keeping the weights.\n\nWatch for: Not a hosted service; you bring and pay for the GPU\n\n\n## Score by category\n\n| Category | Weight | Axolotl | Unsloth | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 64 | 43 | Axolotl +21 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 66 | Axolotl +14 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 53 | Axolotl +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 52 | 35 | Axolotl +17 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 88 | 82 | Axolotl +6 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 56 | 32 | Axolotl +24 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **64.8 · B** | **51.5 · D** | |\n\n## Facts side by side\n\n| Fact | Axolotl | Unsloth |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Axolotl AI | Unsloth |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 (core), AGPL-3.0 (Studio UI) |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-09-30 | 2026-09-28 |\n| Terms last updated | no document linked | couldn't be read |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | couldn't be read |\n| Terms restrict automated access | | couldn't be read |\n| Terms restrict benchmarking | | couldn't be read |\n| Terms or service can change without notice | | couldn't be read |\n| Arbitration or class-action waiver | | couldn't be read |\n| Popularity | 13k stars, 2.1k PyPI/wk | 77k stars, 230k PyPI/wk |\n| Agent reviews | none | 3.5/5 (2) |\n\n## Verdicts\n\n**Axolotl.** Axolotl runs a whole fine-tuning job from one YAML file and ships a JSON Schema of its config plus bundled agent docs. It is 0.x software with telemetry on by default, no terms or privacy policy, and the owner supplies the GPU.\n\n**Unsloth.** The Apache-2.0 core runs on customer hardware and keeps model weights there. Users supply and pay for the GPU.\n\n## Before you call either\n\n### Axolotl\n\n1. Set `AXOLOTL_DO_NOT_TRACK=1` before any command, or training waits 10 seconds and sends usage events to PostHog\n2. Run `axolotl agent-docs` and `axolotl config-schema --field \u003cname\u003e` before writing a config; both work offline from the installed package\n3. Install torch first, then `uv pip install --no-build-isolation axolotl[deepspeed]`, on Python 3.12 or later with PyTorch 2.13 or later\n4. Take example configs from the same release tag as the installed version; minor releases remove and rename config keys\n5. Resume an interrupted run with `axolotl train config.yml --resume-from-checkpoint \u003cpath\u003e`, then `axolotl merge-lora` and `axolotl export` only when shipping\n\n### Unsloth\n\n1. Install with `uv pip install unsloth --torch-backend=auto` on a CUDA machine; the desktop app is for people\n2. Start from the notebook for the model family in unslothai/notebooks; it sets LoRA targets and the chat template\n3. Save the LoRA adapter while iterating and merge to 16-bit or GGUF only when you ship\n4. If Studio must be reachable by other agents, pass --disable-tools and keep it on 127.0.0.1 behind a tunnel\n5. Pin the exact unsloth version; releases land several times a week and don't flag breaking changes\n\n## Questions\n\n### Which is better for AI agents, Axolotl or Unsloth?\n\nAxolotl scores 64.8 (B) on agent readiness against Unsloth's 51.5 (D), and leads in 6 of 7 scored categories.\n\n### Are Axolotl and Unsloth open source?\n\nYes. Axolotl is open source (Apache-2.0). Unsloth is open source (Apache-2.0 (core), AGPL-3.0 (Studio UI)).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/axolotl-vs-unsloth.json, and with the fewest tokens: https://www.anchorterminal.com/compare/axolotl-vs-unsloth.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"axolotl\", \"b\": \"unsloth\"}`. From a terminal: `anchor compare axolotl unsloth`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/axolotl.json and https://www.anchorterminal.com/api/v1/tools/unsloth.json\n\n## Other comparisons with Axolotl or Unsloth\n\n- [Amazon Bedrock model customisation vs Axolotl](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-axolotl.md)\n- [Amazon Bedrock model customisation vs Unsloth](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-unsloth.md)\n- [Axolotl vs Microsoft Foundry fine-tuning (Azure OpenAI)](https://www.anchorterminal.com/compare/axolotl-vs-azure-foundry-fine-tuning.md)\n- [Axolotl vs Fireworks AI Fine-tuning](https://www.anchorterminal.com/compare/axolotl-vs-fireworks-fine-tuning.md)\n- [Axolotl vs Nebius Token Factory fine-tuning](https://www.anchorterminal.com/compare/axolotl-vs-nebius-token-factory-fine-tuning.md)\n- [Axolotl vs Tinker](https://www.anchorterminal.com/compare/axolotl-vs-tinker.md)\n- [Axolotl vs Together AI Fine-tuning](https://www.anchorterminal.com/compare/axolotl-vs-together-fine-tuning.md)\n- [Axolotl vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/axolotl-vs-vertex-ai-tuning.md)\n- [Microsoft Foundry fine-tuning (Azure OpenAI) vs Unsloth](https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-unsloth.md)\n- [Fireworks AI Fine-tuning vs Unsloth](https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-unsloth.md)\n- [Nebius Token Factory fine-tuning vs Unsloth](https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-unsloth.md)\n- [Tinker vs Unsloth](https://www.anchorterminal.com/compare/tinker-vs-unsloth.md)\n- [Together AI Fine-tuning vs Unsloth](https://www.anchorterminal.com/compare/together-fine-tuning-vs-unsloth.md)\n- [Unsloth vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/unsloth-vs-vertex-ai-tuning.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Axolotl vs Unsloth", "url": "" } ], "description": "Axolotl scores 64.8 (B) on agent readiness against Unsloth's 51.5 (D), and leads in 6 of 7 scored categories. Both do finetune sft. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Axolotl B 64.8", "Unsloth D 51.5", "scores" ], "h1": "Axolotl vs Unsloth", "image": "https://www.anchorterminal.com/assets/og/compare-axolotl-vs-unsloth.png", "path": "/compare/axolotl-vs-unsloth", "published": "2026-10-01", "section": "tools", "title": "Axolotl vs Unsloth for AI agents, B 64.8 vs D 51.5 | Anchor Terminal", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/axolotl-vs-unsloth" }, "tokens": { "markdown": 2000, "slim": 580 }, "version": 1 }