AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF

<picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/ankit-aglawe/parable-assets/main/parableheaderdark.png"> <img alt="Parable" src="https://raw.githubusercontent.com/ankit-aglawe/parable-assets/main/parable_header.png"> </picture>

🪶 Parable-Qwen3-8B — trained on genuine Claude Fable 5 agent traces

The largest Parable: planning, tool use, and <think> 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

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):

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:

llama-cli -m Parable-Qwen3-8B-Claude-Fable-5-GGUF-Q4_K_M.gguf --jinja \
  -p "Write a bash one-liner to find the 10 largest files in a directory tree."

LM Studio: lms get parable/qwen3-fable, search "parable" in-app, or paste this repo URL (parable on LM Studio Hub).

Python (llama-cpp-python):

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF",
    filename="*Q4_K_M.gguf", n_ctx=8192,
)
out = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Write a Python function that retries an HTTP request with exponential backoff."}],
    max_tokens=3000, temperature=0.7,
)
print(out["choices"][0]["message"]["content"])

Thinking mode

Every answer opens with a <think>...</think> reasoning block — native to Qwen3, reinforced by this fine-tune. llama.cpp's --jinja chat mode separates it automatically; strip it before showing replies to end users. Sampling: temperature 0.7, topp 0.95, and budget `maxtokens` generously (at least 2500) — trace-trained models think at length before answering.

How it measures

Held-out test split, identical evaluation code and context length for base and fine-tune:

Qualitative review (34 coding/terminal/debugging prompts, strictly graded by mentally executing every answer): 23/34 fully correct, 30/34 correct or partially correct — the highest fully-correct score in the series. We publish these numbers because strict qualitative grading is rare in this niche; judge accordingly.

For reference, the strongest published fine-tune on this data family (a 9B) reports 0.71 validation loss; this release measures 0.712 under our stricter 1,024-token evaluation. Cross-repo numbers are indicative only: splits, tokenizers, and context lengths differ (ours is measured at 1,024 tokens).

What it's trained on

• —Glint-Research/Fable-5-traces — 4.4k real Claude Fable 5 coding-agent session traces with <think> reasoning and tool calls (AGPL-3.0)
• —Roman1111111/gpt5.5-terminal — terminal-agent task solutions (MIT)

Every example passed a quality gate (schema validation, secrets scrub, length filtering) before training. QLoRA fine-tune (NF4, sequence length 1024) trained on a single 16 GB GPU, quantized with llama.cpp.

Good to know

• —Weakest on config-file generation and stateful shell logic (4/34 in our eval: Makefile targets, log-watcher scripts, Dockerfile layer ordering) — review generated configs before use.
• —Fine-tuned at 1,024-token sequences; the base 128K context stays fully available, so long sessions work, with the fine-tuned behavior strongest in the opening turns.
• —Inherits Qwen3-8B's base behaviors and knowledge cutoff. As with any local model, treat generated commands and code as drafts to review.

Evaluation

Function calling (BFCL V3, AST subset)

Measured 2026-07-29: bfcl-eval at gorilla main, prompting mode, Q4KM GGUFs served by llama.cpp on a T4, base and Parable under the identical harness. Categories: simplepython / multiple / parallel / parallelmultiple (400/200/200/200 items). Raw generations and score files: parable-v2-artifacts under verify/bfcl/.

A 2.3 to 5.0 point trade per category: prose-trace SFT costs a little function-calling sharpness, as this card's evaluation note predicts. If you need maximum tool-calling accuracy, use the base; this variant buys the reasoning voice.

Base & license

Weights: Apache-2.0 (inherited from Qwen/Qwen3-8B). Training data: Fable-5-traces AGPL-3.0, gpt5.5-terminal MIT — since those traces originate from third-party assistants, the providers' terms may apply to downstream training and distillation; if you plan to build on this model commercially, confirm your use aligns with those terms.

Get Parable

Citation

The recipe, evaluation methodology and failure analysis behind this model are documented in the tech report:

Aglawe, A. (2026). Agent-Trace Fine-Tuning of Small Language Models under Constrained Compute. Zenodo. doi:10.5281/zenodo.21676407

@misc{aglawe2026agenttrace,
  author    = {Aglawe, Ankit},
  title     = {Agent-Trace Fine-Tuning of Small Language Models under Constrained Compute},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.21676407},
  url       = {https://doi.org/10.5281/zenodo.21676407}
}

Acknowledgements

Glint-Research & Roman1111111 for the open trace data · Qwen for the base · empero-ai whose Qwable recipe the Parable series follows · llama.cpp

Six gigabytes. Real Fable 5 reasoning. Yours, offline, right now.

ollama run hf.co/AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF:Q4_K_M

More on the Parable models: ankitaglawe.com/parable