Qwen3.6 35B A3B Heretic MOE v3 needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 10.0 GB (IQ2_XXS) to 71.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwen3.6 35B A3B Heretic MOE v3 – 35.5B parameter causal language model with vision encoder
Qwen3.6 35B A3B Heretic MOE v3 is a causal language model with a vision encoder. It contains 35.5B total parameters, 3B active parameters, and supports a native context length of 262,144 tokens. The model is released under Apache‑2.0.
Good at
- Vision‑enabled language tasks
- Large context reasoning
- Mixture‑of‑experts inference
Limits
- No vision support in quantized files
- Requires 8,000‑token context for memory estimates
- License is Apache‑2.0
Best for
- Multimodal content generation
- Long‑form reasoning
- Agentic coding
Who it’s for. Developers needing a large, vision‑enabled language model with extended context. The model is suitable for applications that benefit from mixture‑of‑experts architecture and agentic coding capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 10.0 GB | 11.2 GB | Too big | Get file → | |
| IQ2_XXS | 10.0 GB | 11.2 GB | Too big | Get file → | |
| IQ3_M | 15.8 GB | 17.0 GB | Too big | Get file → | |
| IQ3_M | 15.8 GB | 17.0 GB | Too big | Get file → | |
| IQ4_XS | 19.2 GB | 20.4 GB | Too big | Get file → | |
| IQ4_XS | 19.2 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → | |
| F16 | 71.1 GB | 72.3 GB | Too big | Get file → | |
| F16 | 71.1 GB | 72.3 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ2_XXS (file size 9.97 GB, estimated 11.2 GB at 8k context). For 16‑GB VRAM, use IQ3_M (15.81 GB, 17 GB) or IQ4_XS (19.18 GB, 20.4 GB). For 32‑GB VRAM, use Q6_K (29.21 GB, 30.4 GB).
What GPU do you need for Qwen3.6 35B A3B Heretic MOE v3?
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: the best quant that fits is IQ2_XXS (10.0 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_XXS (10.0 GB file, about 11.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).
Which Qwen3.6 35B A3B Heretic MOE v3 quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 35B A3B Heretic MOE v3: it balances file size and quality well. Here it is a 21.7 GB file.
The Q8_0 file is 37.8 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 IQ2_XXS at 10.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 35B A3B Heretic MOE v3
How much VRAM does Qwen3.6 35B A3B Heretic MOE v3 need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 MOE v3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B Heretic MOE v3 GGUF?
It depends on the quant: IQ2_XXS is 10.0 GB, IQ2_XXS is 10.0 GB, IQ3_M is 15.8 GB, IQ3_M is 15.8 GB, IQ4_XS is 19.2 GB, IQ4_XS is 19.2 GB and 8 more.
What context length does Qwen3.6 35B A3B Heretic MOE v3 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 Qwen3.6 35B A3B Heretic MOE v3 GGUF?
The files are on Hugging Face in the DmitryDB/Qwen3.6-35B-A3B-Heretic-MOE-v3 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 MOE v3 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 smallest quantized file IQ2_XXS is 9.97 GB and requires about 11.2 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
Does the model support vision tasks?
Yes, the model has a vision encoder and detected abilities include vision.
What license applies to this model?
The model is released under the Apache‑2.0 license.