Qwen3.5 4B Heretic needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 31 quants, from 0.0 GB to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Qwen3.5 4B Heretic – a multimodal LLM with vision, reasoning, and tool use
Qwen3.5 4B Heretic is a causal language model with a vision encoder. It supports reasoning, tools, and vision tasks. The model is based on the Qwen3.5 architecture and trained with a context length of 262144 tokens.
Good at
- Vision‑language reasoning
- Tool‑enabled workflows
- Multilingual support
Limits
- No dedicated vision API support in llama.cpp
- Requires 8k context for memory estimates
- Apache‑2.0 license limits commercial redistribution
Best for
- Local inference on a single GPU
- Developing vision‑enabled chatbots
- Testing multimodal prompts
Who it’s for. Developers and researchers who need a compact vision‑language model for local deployment. The model is suitable for experimentation and prototyping on consumer hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| IQ1_M | 1.3 GB | 2.8 GB | Fits | Get file → | |
| IQ2_XXS | 1.4 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 1.5 GB | 3.1 GB | Fits | Get file → | |
| IQ2_S | 1.5 GB | 3.1 GB | Fits | Get file → | |
| IQ2_M | 1.6 GB | 3.2 GB | Fits | Get file → | |
| Q2_K | 1.8 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XS | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_S | 2.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_M | 2.2 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 2.4 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_1 | 2.8 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_0 | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_1 | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (file size 1.39 GB, memory 3 GB) or Q4_0 (2.38 GB, 4 GB). For 12 GB VRAM, Q4_K_M (2.71 GB, 4.3 GB) or Q5_K (3.11 GB, 4.7 GB) are good choices. Higher precision quants like Q8_0 (4.48 GB, 6.1 GB) require more memory but give better quality.
What GPU do you need for Qwen3.5 4B 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: the best quant that fits is IQ4_XS (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which Qwen3.5 4B Heretic quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 4B Heretic: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.5 GB, about 1.7 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 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
Source
Frequently asked questions about Qwen3.5 4B Heretic
How much VRAM does Qwen3.5 4B Heretic need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 4B Heretic on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 4B Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.5 GB and 25 more.
What context length does Qwen3.5 4B 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 4B Heretic GGUF?
The files are on Hugging Face in the ZuzeTt/Qwen3.5-4B-heretic-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 4B 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 4B Heretic on 8 GB VRAM?
Yes, with a quant such as IQ2_XXS or Q4_0 the estimated VRAM usage is around 3–4 GB at 8k context.
Does the model support vision tasks in llama.cpp?
The model includes a vision encoder, but llama.cpp does not expose a dedicated vision API; vision prompts must be handled manually.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing commercial use with attribution.