A production-grade, fully fine-tuned 27B language model — engineered for advanced reasoning, software engineering, and structured problem solving.
QwenFable (also known as Qwable 27B) is a full fine-tune of
unsloth/Qwen3.6-27B
on a proprietary 105-trillion-token synthetic corpus generated using Claude Mythos and
Fable 5. The result is a model optimized for real-world capability over benchmark scores.
Unlike adapter-based releases, this is a complete merged Hugging Face checkpoint — deployable natively across Transformers, vLLM, TGI, llama.cpp, Ollama, LM Studio, and more.
Decomposes complex problems into clear logical chains before answering.
Produces production-quality code with strong debugging and architecture skills.
Handles algorithm design, system architecture, and technical documentation.
Generates clear, technically accurate, logically organized responses.
Strong adherence to instructions with deterministic output formatting.
Designed for agent workflows, tool calling, and structured interactions.
# Pull and run with Ollama
ollama run hf.co/JinglanWeb3/QwenFable:Q4_K_M
# Start an OpenAI-compatible server llama-server -hf JinglanWeb3/QwenFable:Q4_K_M # Or chat directly in the terminal llama-cli -hf JinglanWeb3/QwenFable:Q4_K_M
1. Open LM Studio 2. Search for "JinglanWeb3/QwenFable" 3. Select the Q4_K_M quant 4. Load and chat
from transformers import AutoModel, AutoTokenizer model = AutoModel.from_pretrained( "JinglanWeb3/QwenFable", device_map="auto", torch_dtype="auto" ) tokenizer = AutoTokenizer.from_pretrained("JinglanWeb3/QwenFable")
⚠️ You need to accept the gated access terms on the model page first.
import llama_cpp llm = llama_cpp.Llama.from_pretrained( repo_id="JinglanWeb3/QwenFable", filename="Qwable-27b_Q4_K_M.gguf", n_ctx=8192, n_gpu_layers=-1, # offload all layers to GPU ) response = llm.create_chat_completion( messages=[{ "role": "user", "content": "Write a Python function to merge two sorted lists." }] ) print(response["choices"][0]["message"]["content"])
import llama_cpp llm = llama_cpp.Llama.from_pretrained( repo_id="JinglanWeb3/QwenFable", filename="Qwable-27b_Q4_K_M.gguf", n_ctx=8192, n_gpu_layers=-1, # Enable reasoning extraction chat_format="qwen", ) # The model outputs reasoning insidetags stream = llm.create_chat_completion( messages=[{ "role": "user", "content": "Explain quantum entanglement simply." }], stream=True, ) for chunk in stream: delta = chunk["choices"][0]["delta"] if "content" in delta: print(delta["content"], end="")
| Base Model | unsloth/Qwen3.6-27B |
| Architecture | Qwen 3.6 |
| Parameters | 27 Billion |
| Training Method | Full Supervised Fine-Tuning |
| Training Corpus | Claude Mythos + Fable 5 Synthetic (105T tokens) |
| Context Length | 262,144 tokens |
| Precision | BF16 |
| GGUF Quant | Q4_K_M (16.5 GB) |
| License | MIT |
| Languages | en, zh, ko, hi, sa, ta, te, fr, es, mr, gd, br |
This Space is currently a static page. With a community GPU grant from Hugging Face, it can become a full interactive ZeroGPU demo. Open a discussion below to apply.
Apply for GPU Grant