QW

Qwen3.6 35B A3B Heretic Cerebellum

QwenGGUF by deucebucketUpdated 2026-07-05
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant12.0 GB
Quick answer

Qwen3.6 35B A3B Heretic Cerebellum needs about 13.1 GB of memory at Q3_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 12.0 GB (Q3_K_M) to 14.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.6 35B A3B Heretic Cerebellum – a decensored, vision‑capable GGUF model

Qwen3.6 35B A3B Heretic Cerebellum is a 34.7 billion‑parameter model with a 3 billion‑parameter mixture of experts. It supports vision and is released under Apache‑2.0. The model is available in two quantizations for GGUF use.

Good at

  • Vision and multimodal tasks
  • Decensored responses
  • Large context handling

Limits

  • Requires a vision projector for image/video use
  • Large VRAM needed for full precision
  • No explicit language support list

Best for

  • Multimodal content generation
  • Research on decensored LLMs
  • Applications needing large context

Who it’s for. Developers and researchers who need a decensored, vision‑capable LLM with a large context window. The model is suitable for projects that can accommodate its memory requirements and are comfortable with an Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M12.0 GB 13.1 GB
Too big Get file →
—14.5 GB 15.6 GB
Too big Get file →

For 8 GB VRAM use the Q3_K_M quantization (11.96 GB file, ~13.1 GB memory at 8k context). If you have 12 GB VRAM, the 14.47 GB quantization (~15.6 GB memory) is the next option. Memory estimates are approximate.

What GPU do you need for Qwen3.6 35B A3B Heretic Cerebellum?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (14.5 GB file, about 15.6 GB in use).

Which Qwen3.6 35B A3B Heretic Cerebellum quant should you choose?

Q3_K_M (12.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bydeucebucket
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,107
Last updated2026-07-05

Frequently asked questions about Qwen3.6 35B A3B Heretic Cerebellum

How much VRAM does Qwen3.6 35B A3B Heretic Cerebellum need?

About 13.1 GB at Q3_K_M with an 8K context window. That is the 12.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3.6 35B A3B Heretic Cerebellum on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 35B A3B Heretic Cerebellum GGUF?

It depends on the quant: Q3_K_M is 12.0 GB, file is 14.5 GB.

What context length does Qwen3.6 35B A3B Heretic Cerebellum support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Qwen3.6 35B A3B Heretic Cerebellum GGUF?

The files are on Hugging Face in the deucebucket/Qwen3.6-35B-A3B-Heretic-Cerebellum-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3.6 35B A3B Heretic Cerebellum use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

No, the smallest quantization requires at least 13.1 GB of VRAM at 8k context.

Does the model support image input?

Yes, but a vision projector file is required for multimodal use.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from deucebucket

All by deucebucket →

More Qwen models

All Qwen →

Other large models

All large models →