Store › model › LLM
Parable-Qwen3-8B-Claude-Fable-5-GGUF
by AnkitAI · source Hugging Face · updated 2026-09-22
apache-2.04.7 GB~6 GB RAMsource aliveunlabeled
🪶 Parable-Qwen3-8B — trained on genuine Claude Fable 5 agent traces
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF
- License: apache-2.0
- Requirements: about 6 GB of RAM, 4.7 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
ggufqloraagenticagentcodingtool-useterminalreasoningthinkingclaudeclaude-fable-5distillationtrace-trainingllama.cppollamalm-studio
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
Numbers as of 2026-10-02 21:00 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
Parable-Qwen3-8B-Claude-Fable-5-GGUF-F16.gguf | F16 | 15 GB |
Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf | Q4_K_M | 4.7 GB |
Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q5_K_M.gguf | Q5_K_M | 5.4 GB |
Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q6_K.gguf | Q6_K | 6.3 GB |
Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q8_0.gguf | Q8_0 | 8.1 GB |
From the source README
🪶 Parable-Qwen3-8B — trained on genuine Claude Fable 5 agent traces
The largest Parable: planning, tool use, and `` reasoning distilled from real Claude Fable 5 and GPT-5.5 agent sessions — not synthetic Q&A.
> ~6 GB of RAM is all you need. Laptop, mid-range GPU, yesterday's desktop — the Q4 build runs
> anywhere with that much headroom. One command and you have a private, offline reasoning model on your machine:
>
> ```bash
> ollama run hf.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF:Q4_K_M
> ```
Announcements
🔮 v2 is coming. The 3B just got the v2 treatment (13× corpus, rebuilt recipe) — the same upgrade lands here next. Same links, in-place.
📦 Full family. This 8B is the largest Parable, alongside Parable-Qwen3-4B — browse the full collection for every size, quant, and eval report.
Pick your size
| File | Size | Fits in | Notes |
|---|---|---|---|
| Q4_K_M | 4.8 GB | ~6 GB RAM/VRAM | ⭐ Recommended — best size/quality balance |
| Q5_K_M | 5.6 GB | ~7 GB | Higher quality |
| Q6_K | 6.4 GB | ~7.5 GB | Near-lossless |
| Q8_0 | 8.3 GB | ~9.5 GB | Maximum quality |
Full-precision safetensors (vLLM, transformers, further fine-tuning): Parable-Qwen3-8B-Claude-Fable-5
How to run it
Ollama (chat template ships inside the GGUF — zero config):
```bash
ollama run parable/qwen3-fable:8b
# or straight from this repo:
ollama run hf.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF:Q4_K_M
```
llama.cpp:
```bash
llama-cli…
Card id model:hf:AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF · collected 2026-10-02 21:00 UTC · JSON