{"v":1,"id":"model:hf:AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF","slug":"model-ankitai-parable-qwen3-8b-claude-fable-5-gguf","kind":"model","category":"llm","title":"Parable-Qwen3-8B-Claude-Fable-5-GGUF","summary":"🪶 Parable-Qwen3-8B — trained on genuine Claude Fable 5 agent traces","source":{"provider":"hf","ref":"AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF","url":"https://huggingface.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF","rev":"6d07b3bc329fb55e5d1bf2ddcb9244f4e5753553","fetchedAt":"2026-10-02T21:00:35.564Z","etag":"W/\"1d9a-taXHmG6/qWrEuxkLAtVOp2QeVtY\""},"author":{"name":"AnkitAI","url":"https://huggingface.co/AnkitAI"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":455969,"downloadsWeek":327838,"likes":5,"takenAt":"2026-10-02T21:00:35.564Z"},"tags":["gguf","qlora","agentic","agent","coding","tool-use","terminal","reasoning","thinking","claude","claude-fable-5","distillation","trace-training","llama.cpp","ollama","lm-studio","qwen3","text-generation","en","dataset:Glint-Research/Fable-5-traces","dataset:Roman1111111/gpt5.5-terminal","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2026-09-22T12:41:07.000Z","collectedAt":"2026-10-02T21:00:35.564Z","review":{"numbers":["455,969 downloads on Hugging Face","5 likes","license apache-2.0","4.7 GB for Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:00:35.564Z","http":200},"description":"# 🪶 Parable-Qwen3-8B — trained on genuine Claude Fable 5 agent traces\n\n### The largest Parable: planning, tool use, and `` reasoning distilled from real Claude Fable 5 and GPT-5.5 agent sessions — not synthetic Q&A.\n\n> **~6 GB of RAM is all you need.** Laptop, mid-range GPU, yesterday's desktop — the Q4 build runs\n> anywhere with that much headroom. One command and you have a private, offline reasoning model on your machine:\n>\n> ```bash\n> ollama run hf.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF:Q4_K_M\n> ```\n\n---\n\n## Announcements\n\n**🔮 v2 is coming.** The 3B just got the v2 treatment (13× corpus, rebuilt recipe) — the same upgrade lands here next. Same links, in-place.\n\n**📦 Full family.** This 8B is the largest Parable, alongside [Parable-Qwen3-4B](https://huggingface.co/AnkitAI/Parable-Qwen3-4B-Claude-Fable-5-GGUF) — browse the [full collection](https://huggingface.co/collections/AnkitAI/parable-6a4fac60f4b35afca3019621) for every size, quant, and eval report.\n\n---\n\n## Pick your size\n\n| File | Size | Fits in | Notes |\n|---|---|---|---|\n| [Q4_K_M](./Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf) | 4.8 GB | ~6 GB RAM/VRAM | ⭐ **Recommended** — best size/quality balance |\n| [Q5_K_M](./Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q5_K_M.gguf) | 5.6 GB | ~7 GB | Higher quality |\n| [Q6_K](./Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q6_K.gguf) | 6.4 GB | ~7.5 GB | Near-lossless |\n| [Q8_0](./Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q8_0.gguf) | 8.3 GB | ~9.5 GB | Maximum quality |\n\nFull-precision safetensors (vLLM, transformers, further fine-tuning): [Parable-Qwen3-8B-Claude-Fable-5](https://huggingface.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5)\n\n## How to run it\n\n**Ollama** (chat template ships inside the GGUF — zero config):\n```bash\nollama run parable/qwen3-fable:8b\n# or straight from this repo:\nollama run hf.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF:Q4_K_M\n```\n\n**llama.cpp:**\n```bash\nllama-cli…\n\nSource: https://huggingface.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF","install":{"kind":"model","hfId":"AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF","gated":false,"format":"gguf","files":[{"name":"Parable-Qwen3-8B-Claude-Fable-5-GGUF-F16.gguf","size":16388043744,"quant":"F16","sha256":"c04693701d9d0a36915f17f2d3cf40dfab4a5bc81b7bb7a4e298cb0e16c2d88e"},{"name":"Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf","size":5027783648,"quant":"Q4_K_M","sha256":"d25c4c1f4f009fe4c155ae841d6b63df4f6f3dd4502fc3263f2fcf5194855ebf"},{"name":"Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q5_K_M.gguf","size":5851112416,"quant":"Q5_K_M","sha256":"e77c26c5708e1ff69cea55c591c5631f6ab64935bab16b69ee605b70298289b9"},{"name":"Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q6_K.gguf","size":6725899232,"quant":"Q6_K","sha256":"5cc656273cfd34953afe3490f2157d5a4473a58582af359c51c8ad556e86e862"},{"name":"Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q8_0.gguf","size":8709518304,"quant":"Q8_0","sha256":"91972a293e85fcd6b15dc86961ebc86ad796b41922446f2e86fad0f1c69d33b8"}],"totalBytes":42702357344,"suggestedFile":"Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf","requirements":{"ramGb":6,"diskBytes":5027783648,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"],"command":"lsh models install hf:AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF"}}