Qwen3.6 35B A3B Abliterated Heretic BF16 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 4 quants, from 21.2 GB (Q4_K_M) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.6 35B A3B Abliterated Heretic BF16 – a vision‑enabled sparse‑MoE model
Qwen3.6 35B A3B Abliterated Heretic BF16 is a 35.95B sparse‑MoE vision‑language model. It contains 34.7B total parameters with 3B active per token and supports a native context length of 262,144 tokens, extendable to 1,010,000 tokens. The model is released under Apache‑2.0.
Good at
- Vision‑enabled multimodal tasks
- Large context reasoning
- Sparse‑MoE efficient inference
Limits
- No default refusal behavior – user responsibility
- Requires 8‑bit or higher quant for practical VRAM use
- Large VRAM needed for BF16
- No explicit language list
Best for
- Vision‑language inference on local GPU
- Long‑form multimodal content generation
- Fine‑tuning with small VRAM budgets
Who it’s for. Developers needing a multimodal LLM with large context and sparse‑MoE efficiency. Suitable for local deployment with llama.cpp or compatible runtimes. Users must handle the removed refusal behavior responsibly.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| BF16 | 69.4 GB (2 parts) | 70.5 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_M (21.17 GB file, ~22.3 GB memory at 8K context). For 16‑GB VRAM, Q6_K (28.51 GB file, ~29.7 GB memory) is suitable. BF16 requires at least 70.5 GB memory and is best for high‑end GPUs.
What GPU do you need for Qwen3.6 35B A3B Abliterated Heretic BF16?
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_M (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which Qwen3.6 35B A3B Abliterated Heretic BF16 quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 35B A3B Abliterated Heretic BF16: it balances file size and quality well. Here it is a 21.2 GB file.
The Q8_0 file is 36.9 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 35B A3B Abliterated Heretic BF16
How much VRAM does Qwen3.6 35B A3B Abliterated Heretic BF16 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 Qwen3.6 35B A3B Abliterated Heretic BF16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B Abliterated Heretic BF16 GGUF?
It depends on the quant: Q4_K_M is 21.2 GB, Q6_K is 28.5 GB, Q8_0 is 36.9 GB, BF16 is 69.4 GB.
What context length does Qwen3.6 35B A3B Abliterated Heretic BF16 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 Qwen3.6 35B A3B Abliterated Heretic BF16 GGUF?
The files are on Hugging Face in the lhca521/Qwen3.6-35B-A3B-Abliterated-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 Qwen3.6 35B A3B Abliterated Heretic BF16 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 Qwen3.6 35B A3B Abliterated Heretic BF16 on 8 GB VRAM?
No. The BF16 quant requires ~70.5 GB memory at 8K context. Use Q4_K_M or Q6_K instead.
Does this model support vision tasks?
Yes. It includes a vision encoder and a matching multimodal projector for llama.cpp vision use.
What license applies to this model?
Apache‑2.0, inherited from the base Qwen3.6‑35B‑A3B model.