Model Intelligence Sheet
EnclaveHost/fable-fusion-27b-mtp-gguf overview
Fable Fusion 27B MTP GGUF Q5 K M quantization of DavidAU/Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU NEO MAX MTP GGUF https://huggingface.co/DavidAU…
Runs locally from ~19.73 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Fable-Fusion-27B-MTP-Q5_K_M.gguf | GGUF | Q5_K_M | 19.73 GB | Download |
Model Details
| Model ID | EnclaveHost/fable-fusion-27b-mtp-gguf |
|---|---|
| Author | EnclaveHost |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-30B-A3B |
| Last modified | 2026-07-25T06:00:14.000Z |
Model README
---
license: apache-2.0
tags:
- gguf
- qwen3.6
- mtp
- fine-tune
base_model: Qwen/Qwen3-30B-A3B
---
Fable Fusion 27B MTP GGUF
Q5_K_M quantization of DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF, packaged as an Enclave Host model volume.
Multi-token prediction (MTP) variant: the GGUF carries the model's trained MTP head for speculative self-drafting.
- Architecture: Qwen3.6 27B (hybrid SSM/attention)
- Quantization: Q5_K_M with MTP head
- Tokenizer: Qwen3.x (vocab 248320)
Run EnclaveHost/fable-fusion-27b-mtp-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models