tvall43/Qwen3.6-35B-A3B-heretic 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 6 quants, from 16.8 GB (Q3_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: 35B parameter LLM with vision and MoE
Qwen3.6-35B-A3B is a causal language model with a vision encoder and a mixture of experts architecture. It contains 34.7B total parameters, with 3B active during inference, and supports a native context length of 262,144 tokens.
Good at
- Advanced reasoning
- Tool usage
- Vision tasks
Limits
- Requires large VRAM for full precision
- License is apache-2.0
- No native support for 8k context in low‑precision quants
Best for
- Complex coding assistance
- Multimodal content generation
- Large‑scale data analysis
Who it’s for. Developers and researchers needing a versatile, open‑weight model that combines language and vision capabilities. The model is suitable for building agentic applications and advanced coding assistants.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 16.8 GB | 17.9 GB | Too big | Get file → | |
| MXFP4_MOE | 19.8 GB | 21.0 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q5_K_M | 24.7 GB | 25.9 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| BF16 | 69.4 GB | 70.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_M (file size 16.76 GB, estimated memory 17.9 GB at 8k context). For 12 GB VRAM, Q4_K_M (21.17 GB, 22.3 GB). For 16 GB VRAM, MXFP4_MOE (19.79 GB, 21 GB).
What GPU do you need for tvall43/Qwen3.6-35B-A3B-heretic?
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 Q5_K_M (24.7 GB file, about 25.9 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 tvall43/Qwen3.6-35B-A3B-heretic quant should you choose?
Q4_K_M is the usual starting point for tvall43/Qwen3.6-35B-A3B-heretic: 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.
If memory is tight, the smallest file is Q3_K_M at 16.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about tvall43/Qwen3.6-35B-A3B-heretic
How much VRAM does tvall43/Qwen3.6-35B-A3B-heretic 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 tvall43/Qwen3.6-35B-A3B-heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of tvall43/Qwen3.6-35B-A3B-heretic GGUF?
It depends on the quant: Q3_K_M is 16.8 GB, MXFP4_MOE is 19.8 GB, Q4_K_M is 21.2 GB, Q5_K_M is 24.7 GB, Q8_0 is 36.9 GB, BF16 is 69.4 GB.
What context length does tvall43/Qwen3.6-35B-A3B-heretic 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 tvall43/Qwen3.6-35B-A3B-heretic GGUF?
The files are on Hugging Face in the tvall43/Qwen3.6-35B-A3B-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 tvall43/Qwen3.6-35B-A3B-heretic 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?
The Q3_K_M quant requires about 17.9 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
What is the native context length?
262,144 tokens, extensible up to 1,010,000 tokens with extensions.
Is the model licensed for commercial use?
Yes, it is licensed under apache-2.0, which permits commercial use.