shuhulx/Qwopus3.5-4B-Coder-Fable5-v1-GGUF

<div align="center">

💻 Qwopus3.5-4B-Coder-Fable5-v1 GGUF

GGUF builds for llama.cpp, LM Studio, and local inference

<p><b>Fable-5 traces</b> · <b>agentic coding</b> · <b>tool use</b> · <b>debugging</b></p>

</div>

Overview

Qwopus3.5-4B-Coder-Fable5-v1 is a Fable-5 trace continuation of `Jackrong/Qwopus3.5-4B-Coder`.

The base model, Qwopus3.5-4B-Coder, is a compact Qwen3.5-based coding model trained for reasoning, tool use, function calling, coding workflows, and agent-style behavior.

This release continues that model on `Glint-Research/Fable-5-traces`, a dataset of Claude Fable 5 local coding-agent traces. The dataset is heavily oriented around tool-use trajectories, repository work, local command context, code editing, debugging loops, and <think>-style reasoning completions.

The result is a small local coding-agent model intended for:

Files

Typical GGUF files:

• —Qwopus3.5-4B-Coder-Fable5-v1-Q4_K_M.gguf
• —Qwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.gguf
• —Qwopus3.5-4B-Coder-Fable5-v1-mmproj-BF16.gguf

Which file should I use?

llama.cpp

llama-cli \
  -m Qwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.gguf \
  -p "Write a Bash/Read/Edit style plan for debugging a failing Python repo." \
  -n 768 \
  --temp 0.7 \
  --top-p 0.95

llama.cpp Server

llama-server \
  -m Qwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.gguf \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 8192

Then call it with an OpenAI-compatible client:

curl -X POST "http://localhost:8080/v1/chat/completions" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "Qwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.gguf",
    "messages": [
      {"role": "user", "content": "Write a tool-use plan for debugging a Python repo."}
    ],
    "temperature": 0.7,
    "top_p": 0.95
  }'

About the Fable-5 Traces

`Glint-Research/Fable-5-traces` contains Claude Fable 5 coding traces.

The dataset includes fields such as:

uid
source_file
session
model
context
cot
output_type
output
completion
origin

The examples are not simple chat pairs. They are multi-step agent trajectories with local development context, reasoning traces, and tool-use outputs.

Common patterns in the dataset include:

• —user coding requests
• —local-command caveats
• —repository inspection
• —Bash command usage
• —file reads
• —file writes
• —edits
• —debugging passes
• —playtesting / validation loops
• —<think>...</think> reasoning traces
• —tool-use completions

A large portion of the dataset is tool_use style data, which makes it especially relevant for local coding agents and developer automation.

Capabilities

Agentic coding

Designed for coding-agent loops where the model must inspect a repo, plan work, call tools, edit files, and validate changes.

Tool-use style outputs

Works well with prompts that expose structured tools such as:

Bash
Read
Write
Edit
Search
Grep

Debugging and repair

Useful for:

• —finding likely failing files
• —explaining stack traces
• —planning test commands
• —proposing minimal patches
• —iterating after errors

Local-first deployment

The release includes Transformers, GGUF, MLX, and MLX 4-bit formats so it can run in Python, llama.cpp, LM Studio, and Apple Silicon workflows.

Available Releases

Credits

Built on:

• —`Jackrong/Qwopus3.5-4B-Coder` by Jackrong
• —`Glint-Research/Fable-5-traces` by Glint-Research
• —Qwen / Qwen3.5 model family
• —Unsloth
• —Hugging Face
• —llama.cpp
• —mlx-lm