Huihui-Qwen3.6-35B-A3B-abliterated needs about 26.6 GB of memory at Q5_K (a 25.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 21.3 GB (Q4_K) to 71.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Huihui-Qwen3.6-35B-A3B-abliterated – a 35.5B parameter Qwen model with reduced safety filtering
Huihui-Qwen3.6-35B-A3B-abliterated is a 35.5B parameter Qwen model with 3B active mixture‑of‑experts. It supports reasoning, tools, and vision. The model is released under apache‑2.0 and is intended for research and controlled environments.
Good at
- Reasoning tasks
- Tool usage
- Vision processing
Limits
- Reduced safety filtering may produce sensitive content
- Requires large VRAM for full precision
- No default safety guarantees
Best for
- Research on safety‑filtered LLMs
- Controlled testing of vision prompts
- Tool‑integrated dialogue systems
Who it’s for. Researchers and developers who need a large Qwen model with minimal safety filtering for controlled experiments. The model is not suitable for public or commercial deployment without additional safeguards.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 21.3 GB | 22.5 GB | Too big | Get file → | |
| Q5_K | 25.4 GB | 26.6 GB | Too big | Get file → | |
| Q6_K | 29.8 GB | 31.0 GB | Too big | Get file → | |
| BF16 | 71.1 GB (4 parts) | 72.3 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K (21.29 GB file, ~22.5 GB memory at 8 k context). For 12 GB VRAM use Q5_K (25.42 GB file, ~26.6 GB memory). For 16 GB VRAM use Q6_K (29.81 GB file, ~31 GB memory). BF16 requires >72 GB memory and is not recommended for typical consumer GPUs.
What GPU do you need for Huihui-Qwen3.6-35B-A3B-abliterated?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K (21.3 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.8 GB file, about 31.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (29.8 GB file, about 31.0 GB in use).
Which Huihui-Qwen3.6-35B-A3B-abliterated quant should you choose?
Q5_K (25.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_K at 21.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Huihui-Qwen3.6-35B-A3B-abliterated
How much VRAM does Huihui-Qwen3.6-35B-A3B-abliterated need?
About 26.6 GB at Q5_K with an 8K context window. That is the 25.4 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 Huihui-Qwen3.6-35B-A3B-abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Huihui-Qwen3.6-35B-A3B-abliterated GGUF?
It depends on the quant: Q4_K is 21.3 GB, Q5_K is 25.4 GB, Q6_K is 29.8 GB, BF16 is 71.1 GB.
What context length does Huihui-Qwen3.6-35B-A3B-abliterated 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 2.8 GB at 32K.
Where can I download Huihui-Qwen3.6-35B-A3B-abliterated GGUF?
The files are on Hugging Face in the dnnagy/Huihui-Qwen3.6-35B-A3B-abliterated-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 Huihui-Qwen3.6-35B-A3B-abliterated 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 the Q4_K quantized file which requires about 22.5 GB of memory at 8 k context, but 8 GB VRAM is insufficient; a larger GPU is needed.
Does this model support vision?
Yes, it has detected vision ability, but it is experimental and not fully optimized.
Is the model safe for public use?
No, the safety filtering is significantly reduced; it is intended for research and controlled environments only.