Qwen3.6 35B A3B heretic Q4 K M 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. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.6 35B A3B heretic Q4 K M – 35B parameter model with vision and tools
Qwen3.6 35B A3B heretic Q4_K_M is a causal language model with a vision encoder. It contains 34.7B total parameters, 3B active in a mixture‑of‑experts setup. The model supports a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens.
Good at
- Reasoning and problem solving
- Tool usage and code generation
- Vision‑enabled tasks
Limits
- Requires 22.3 GB VRAM at 8k context
- No official vision support in llama.cpp
- License type is other, not open source
Best for
- Developers building agentic coding assistants
- Researchers testing vision‑language models
- Teams needing large context for code review
Who it’s for. This model is suited for developers and researchers who need a large‑parameter, vision‑enabled language model with a mixture‑of‑experts architecture. It is ideal for applications that require extensive context and tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → |
For 8‑GB VRAM, the Q4_K_M quantization is the only available option, requiring 22.3 GB VRAM at 8k context. If you have a larger GPU, the same quantization will still be used; no other quant sizes are provided in the repository.
What GPU do you need for Qwen3.6 35B A3B heretic Q4 K M?
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).
Which Qwen3.6 35B A3B heretic Q4 K M quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 35B A3B heretic Q4 K M: it balances file size and quality well. Here it is a 21.2 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 35B A3B heretic Q4 K M
How much VRAM does Qwen3.6 35B A3B heretic Q4 K M 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 heretic Q4 K M 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 heretic Q4 K M GGUF?
It depends on the quant: Q4_K_M is 21.2 GB.
What context length does Qwen3.6 35B A3B heretic Q4 K M 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 heretic Q4 K M GGUF?
The files are on Hugging Face in the Abiray/Qwen3.6-35B-A3B-heretic-Q4_K_M-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 heretic Q4 K M use?
Hugging Face lists the license as other. 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?
No. The Q4_K_M quantization requires 22.3 GB VRAM at 8k context, which exceeds 8 GB.
Does this model support vision tasks?
Yes, it includes a vision encoder, but llama.cpp support may be limited.
What is the context length of this model?
The native context length is 262,144 tokens, extensible up to 1,010,000 tokens.