BigBang Aquila 35B Merged Abliterated needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 2.0 GB to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
BigBang Aquila 35B Merged Abliterated – a 34.7B parameter Qwen3.6‑style MoE model
BigBang Aquila 35B Merged Abliterated is a 34.7B parameter Qwen3.6‑style mixture of experts model. It supports reasoning and tool usage and has a native context length of 262,144 tokens. The model is released under the apache‑2.0 license.
Good at
- Reasoning and math
- Tool‑calling and web scraping
- Multi‑expert inference
Limits
- No vision support
- Large VRAM requirement for full precision
- Requires transformers>=5.12 and specific kernels for full functionality
Best for
- Complex reasoning tasks
- Automated web‑search agents
- Scientific code generation
Who it’s for. Developers and researchers needing a large, text‑only model with advanced reasoning and tool‑calling capabilities. The model is suitable for applications that can handle its high memory footprint and require a mixture‑of‑experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_0 | 20.7 GB | 21.9 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| — | 21.3 GB | 22.4 GB | Too big | Get file → | |
| Q4_K_M | 22.1 GB | 23.2 GB | Too big | Get file → | |
| — | 22.1 GB | 23.2 GB | Too big | Get file → | |
| — | 22.8 GB | 24.0 GB | Too big | Get file → | |
| — | 23.7 GB | 24.9 GB | Too big | Get file → | |
| — | 24.5 GB | 25.7 GB | Too big | Get file → | |
| BF16 | 69.4 GB | 70.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 20.7 GB, estimated 21.9 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (file size 21.17 GB, estimated 22.3 GB memory) is suitable. For 24 GB VRAM or more, BF16 (file size 69.38 GB, estimated 70.5 GB memory) provides the highest fidelity.
What GPU do you need for BigBang Aquila 35B Merged 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: the best quant that fits is the main file (2.0 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (2.0 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (2.0 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (2.0 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (2.0 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (22.8 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (24.5 GB file, about 25.7 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (24.5 GB file, about 25.7 GB in use).
Which BigBang Aquila 35B Merged Abliterated quant should you choose?
Q4_K_M is the usual starting point for BigBang Aquila 35B Merged Abliterated: it balances file size and quality well. Here it is a 21.2 GB file.
If memory is tight, the smallest file is the first one in the table at 2.0 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 BigBang Aquila 35B Merged Abliterated
How much VRAM does BigBang Aquila 35B Merged Abliterated need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 BigBang Aquila 35B Merged Abliterated on an 8 GB GPU?
Yes, with the smaller files: the 2.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of BigBang Aquila 35B Merged Abliterated GGUF?
It depends on the quant: file is 2.0 GB, Q4_0 is 20.7 GB, Q4_K_M is 21.2 GB, file is 21.3 GB, Q4_K_M is 22.1 GB, file is 22.1 GB and 4 more.
What context length does BigBang Aquila 35B Merged 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 2.7 GB at 32K.
Where can I download BigBang Aquila 35B Merged Abliterated GGUF?
The files are on Hugging Face in the Davd-b01/BigBang-Aquila-35B-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 BigBang Aquila 35B Merged 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_0 quantized GGUF. It requires about 21.9 GB of VRAM at 8 k context, which is close to 8 GB but will need swap or a smaller context.
Does this model support vision?
No. The vision tower was dropped during abliteration; only text inference is available.
What is the native context length?
The model supports up to 262,144 tokens natively.