QW

Qwen3.5 13B Deckard Heretic Uncensored Thinking

QwenGGUF by mradermacherUpdated 2026-03-29
Download on Hugging Face
Parameters12.4B
Context256K
Layers48
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Qwen3.5 13B Deckard Heretic Uncensored Thinking needs about 9.8 GB of memory at Q4_K_M (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 10.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Qwen3.5 13B Deckard Heretic Uncensored Thinking – a 13B uncensored LLM with vision support

This 13B model is built on Qwen 3.5 and fine‑tuned with the Deckard dataset. It supports reasoning and roleplay and includes vision capabilities. The model uses an upgraded Jinja template to reduce repeats and improve tool handling.

Good at

  • Reasoning
  • Roleplay
  • Vision

Limits

  • Large context size 262144 tokens
  • Requires 8‑bit or higher quant for VRAM
  • No explicit image size limits provided

Best for

  • Complex instruction following
  • Interactive roleplay sessions
  • Vision‑enabled content generation

Who it’s for. Developers and researchers needing a large, uncensored model with strong reasoning and vision support. Suitable for local deployment on machines with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.1 GB
Fits Get file →
IQ1_S3.6 GB 5.7 GB
Fits Get file →
IQ1_M3.8 GB 5.9 GB
Fits Get file →
IQ2_XXS4.1 GB 6.2 GB
Fits Get file →
IQ2_XS4.4 GB 6.5 GB
Fits Get file →
IQ2_S4.6 GB 6.7 GB
Fits Get file →
IQ2_M4.8 GB 6.9 GB
Fits Get file →
Q2_K_S5.0 GB 7.1 GB
Fits Get file →
Q2_K5.2 GB 7.3 GB
Tight Get file →
IQ3_XXS5.3 GB 7.4 GB
Tight Get file →
IQ3_XS5.7 GB 7.8 GB
Tight Get file →
Q3_K_S5.7 GB 7.9 GB
Tight Get file →
IQ3_S5.9 GB 8.0 GB
Too big Get file →
IQ3_M6.0 GB 8.1 GB
Too big Get file →
Q3_K_M6.3 GB 8.4 GB
Too big Get file →
Q3_K_L6.7 GB 8.9 GB
Too big Get file →
IQ4_XS7.1 GB 9.2 GB
Too big Get file →
Q4_07.3 GB 9.4 GB
Too big Get file →
Q4_K_S7.3 GB 9.4 GB
Too big Get file →
IQ4_NL7.4 GB 9.5 GB
Too big Get file →
Q4_K_M7.7 GB 9.8 GB
Too big Get file →
Q4_18.0 GB 10.1 GB
Too big Get file →
Q5_K_S8.7 GB 10.8 GB
Too big Get file →
Q5_K_M8.9 GB 11.0 GB
Too big Get file →
Q6_K10.2 GB 12.3 GB
Too big Get file →

For 8‑GB VRAM, use IQ4_K_M (file size 7.73 GB, memory 9.8 GB) or Q4_K_M (file size 6.29 GB, memory 8.4 GB). For 12‑GB VRAM, IQ4_XS (7.1 GB, 9.2 GB) or Q4_0 (7.28 GB, 9.4 GB) are suitable. Larger VRAM allows higher‑quality quants such as Q5_K_M (8.93 GB, 11 GB).

What GPU do you need for Qwen3.5 13B Deckard Heretic Uncensored Thinking?

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: the best quant that fits is the main file (0.0 GB file, about 2.1 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ1_M (3.8 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_S (5.9 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.9 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.2 GB file, about 12.3 GB in use).

Which Qwen3.5 13B Deckard Heretic Uncensored Thinking quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 13B Deckard Heretic Uncensored Thinking: it balances file size and quality well. Here it is a 7.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters12.4B
Layers48
Trained context262,144 tokens
KV cache (fp16)192 KB per token

Frequently asked questions about Qwen3.5 13B Deckard Heretic Uncensored Thinking

How much VRAM does Qwen3.5 13B Deckard Heretic Uncensored Thinking need?

About 9.8 GB at Q4_K_M with an 8K context window. That is the 7.7 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 Qwen3.5 13B Deckard Heretic Uncensored Thinking on an 8 GB GPU?

Yes, with IQ3_S: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 13B Deckard Heretic Uncensored Thinking GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.6 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.1 GB, IQ2_XS is 4.4 GB, IQ2_S is 4.6 GB and 19 more.

What context length does Qwen3.5 13B Deckard Heretic Uncensored Thinking support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Qwen3.5 13B Deckard Heretic Uncensored Thinking GGUF?

The files are on Hugging Face in the mradermacher/Qwen3.5-13B-Deckard-Heretic-Uncensored-Thinking-i1-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 Qwen3.5 13B Deckard Heretic Uncensored Thinking 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?

Yes, using IQ4_K_M or Q4_K_M quants which estimate 9.8 GB or 8.4 GB memory at 8k context.

Does the model support image input?

Yes, it includes vision capabilities and mmproj files are available in the static repository.

Is the model uncensored?

The model is fully uncensored and will not refuse content unless explicitly directed otherwise.

Other GGUFs of Qwen3.5-13B-Deckard-Heretic-Uncensored-Thinking

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →