Qwen3.5 4B heretic imatrix 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 5 quants, from 0.7 GB (Q8_0) to 3.1 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Qwen3.5 4B heretic imatrix – a compact multimodal LLM
Qwen3.5 4B heretic imatrix is a 4‑billion‑parameter causal language model with vision encoder. It supports a 262,144‑token context window and 201 languages. The model is post‑processed with Heretic v1.2.0 for refusal suppression.
Good at
- Coding tasks
- Vision‑language reasoning
- Tool‑calling
Limits
- No vision support in some variants
- Large VRAM needed for higher‑bit quants
- Apache‑2.0 license restricts commercial use without compliance
Best for
- Local inference on edge devices
- Rapid prototyping of multimodal apps
- Educational demonstrations
Who it’s for. Developers needing a small yet capable vision‑language model for local deployment. The model is suitable for research, prototyping, and educational projects where a 4‑B parameter size is advantageous.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.7 GB | 2.3 GB | Fits | Get file → | |
| BF16 | 1.3 GB | 2.9 GB | Fits | Get file → | |
| IQ4_NL | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.71 GB, memory 4.3 GB at 8k context). For 12 GB VRAM, Q5_K_M (3.07 GB, 4.6 GB) offers better quality. If 16 GB VRAM is available, Q8_0 (0.69 GB, 2.3 GB) provides the highest fidelity.
What GPU do you need for Qwen3.5 4B heretic imatrix?
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 BF16 (1.3 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
Which Qwen3.5 4B heretic imatrix quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 4B heretic imatrix: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 0.7 GB, about 0.3 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 Q8_0 at 0.7 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.5 4B heretic imatrix
How much VRAM does Qwen3.5 4B heretic imatrix 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 imatrix on an 8 GB GPU?
Yes, with Q5_K_M: the 3.1 GB file needs about 4.6 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 imatrix GGUF?
It depends on the quant: Q8_0 is 0.7 GB, BF16 is 1.3 GB, IQ4_NL is 2.6 GB, Q4_K_M is 2.7 GB, Q5_K_M is 3.1 GB.
What context length does Qwen3.5 4B heretic imatrix 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 imatrix GGUF?
The files are on Hugging Face in the FadedRedStar/Qwen3.5-4B-heretic-imatrix-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 imatrix 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 imatrix on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires approximately 4.3 GB of VRAM at 8k context.
Does the model support vision tasks?
Yes, the model includes a vision encoder and can process image inputs.
What license applies to this model?
The model is released under the Apache‑2.0 license.