QW

Qwen3.5 9B Heretic

QwenGGUF by SassyDiffusionUpdated 2026-04-18
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant3.5 GB
Quick answer

Qwen3.5 9B Heretic needs about 7.4 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 3.5 GB (IQ2_XXS) to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Qwen3.5 9B Heretic – a multimodal LLM with vision, reasoning, and tools support

Qwen3.5 9B Heretic is a 9B parameter causal language model that includes a vision encoder. It supports reasoning, tool use, and vision tasks. The model is released under the apache-2.0 license and is compatible with llama.cpp.

Good at

  • Vision‑language reasoning
  • Tool‑enabled workflows
  • Multilingual text generation

Limits

  • No explicit vision API support in llama.cpp
  • Requires large VRAM for high‑quality quantizations
  • License is apache‑2.0

Best for

  • Local inference of multimodal prompts
  • Building agents that need vision and reasoning
  • Testing vision‑language benchmarks

Who it’s for. Developers and researchers who need a local, multimodal LLM with vision, reasoning, and tool‑use capabilities. The model is suitable for those who can manage the memory requirements and are comfortable with the apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS3.5 GB 5.0 GB
Fits Get file →
IQ2_M3.7 GB 5.3 GB
Fits Get file →
IQ3_XXS4.2 GB 5.7 GB
Fits Get file →
Q2_K_XL4.3 GB 5.9 GB
Fits Get file →
Q3_K_M4.7 GB 6.2 GB
Fits Get file →
Q3_K_S4.7 GB 6.3 GB
Fits Get file →
Q3_K_XL5.3 GB 6.9 GB
Fits Get file →
IQ4_XS5.3 GB 6.9 GB
Fits Get file →
Q4_05.4 GB 7.0 GB
Fits Get file →
IQ4_NL5.5 GB 7.0 GB
Fits Get file →
Q4_K_S5.6 GB 7.2 GB
Tight Get file →
Q4_K_M5.8 GB 7.4 GB
Tight Get file →
Q4_15.8 GB 7.4 GB
Tight Get file →
Q4_K_XL6.0 GB 7.6 GB
Tight Get file →
Q5_K_S6.5 GB 8.1 GB
Too big Get file →
Q5_K_M6.6 GB 8.2 GB
Too big Get file →
Q5_K_XL6.8 GB 8.4 GB
Too big Get file →
Q6_K7.5 GB 9.0 GB
Too big Get file →
Q6_K_XL8.8 GB 10.3 GB
Too big Get file →
Q8_09.5 GB 11.1 GB
Too big Get file →
Q8_K_XL13.0 GB 14.5 GB
Too big Get file →
BF1617.9 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, use IQ4_XS or Q4_0 (est. 6.9 GB). For 12 GB VRAM, Q4_K_M or Q4_K_XL (est. 7.4–7.6 GB). For 16 GB VRAM, Q5_K_S or Q5_K_M (est. 8.1–8.2 GB).

What GPU do you need for Qwen3.5 9B Heretic?

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: the best quant that fits is Q2_K_XL (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_XL (6.0 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_K_XL (13.0 GB file, about 14.5 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).

Which Qwen3.5 9B Heretic quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 9B Heretic: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 9.5 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_XXS at 3.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bySassyDiffusion
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,072
Last updated2026-04-18

Frequently asked questions about Qwen3.5 9B Heretic

How much VRAM does Qwen3.5 9B Heretic need?

About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.8 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 9B Heretic on an 8 GB GPU?

Yes, with Q4_K_XL: the 6.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 9B Heretic GGUF?

It depends on the quant: IQ2_XXS is 3.5 GB, IQ2_M is 3.7 GB, IQ3_XXS is 4.2 GB, Q2_K_XL is 4.3 GB, Q3_K_M is 4.7 GB, Q3_K_S is 4.7 GB and 16 more.

What context length does Qwen3.5 9B Heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Qwen3.5 9B Heretic GGUF?

The files are on Hugging Face in the SassyDiffusion/Qwen3.5-9B-heretic-ara-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 9B Heretic 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 Qwen3.5 9B Heretic on 8 GB VRAM?

Yes, with a quantization such as IQ4_XS or Q4_0, which estimate 6.9 GB of VRAM at 8k context.

Does this model support vision tasks in llama.cpp?

The model includes a vision encoder, but llama.cpp does not provide a dedicated vision API for this model.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from SassyDiffusion

All by SassyDiffusion →

More Qwen models

All Qwen →

Other small models

All small models →