Qwen3.6-Fallen-Fabulist-35B-A3B-heretic
Cyclone-Labs · Published release · Heretic · GGUF / Transformers / MLX
Model source
Published by Cyclone-Labs on Hugging Face. This index organizes public repository metadata for discovery and comparison. Refer to the publisher and independent testing for actual model behavior.
Declared base model
ornith-ai/Ornith-1.5-35B-A3B ↗
Qwen/Qwen3.6-35B-A3B ↗
Gryphe/WorldSim-Opus-3.6-35B-A3B ↗
ReadyArt/Melody1437-35B-A3B ↗
Hardware and context
Estimated at 21.1 GB VRAM for 35B parameters with 4-bit weights, including 15% weight overhead and 1 GB of baseline headroom. KV cache, context length, multimodal components and concurrency increase actual memory usage.The parameter count was parsed from the model name and has not been independently verified.
Context length: Not stated in public metadata. Please consult the model card.
Download sources and quantized variants
4 repositories| HUGGING FACE REPOSITORY | Format | 30-day downloads | Declared license |
|---|---|---|---|
| mradermacher/Qwen3.6-Fallen-Fabulist-35B-A3B-heretic-GGUF ↗ | GGUF | 3.9K | apache-2.0 |
| mradermacher/Qwen3.6-Fallen-Fabulist-35B-A3B-heretic-i1-GGUF ↗ | GGUF | 2.1K | apache-2.0 |
| Cyclone-Labs/Qwen3.6-Fallen-Fabulist-35B-A3B-heretic ↗ | Transformers | 198 | apache-2.0 |
| fl0rm/Qwen3.6-Fallen-Fabulist-35B-A3B-heretic-mlx-8Bit ↗ | MLX | 58 | apache-2.0 |