Deepwen 3.6 needs about 22.3 GB of memory at its main file (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 10.1 GB to 36.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Deepwen 3.6 – a fine‑tuned Qwen3.6‑35B‑A3B with vision and advanced reasoning
Deepwen 3.6 is a fine‑tuned derivative of Qwen/Qwen3.6‑35B‑A3B, built on a mixture‑of‑experts architecture with 35B total parameters and 3B active. It adds vision capability and a DeepSeek‑style reasoning system for verified answers. The model supports a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens.
Good at
- Vision‑enabled language tasks
- DeepSeek‑style reasoning and verification
- Agentic coding and tool calling
Limits
- Requires large VRAM for full model
- No explicit language list provided
- No non‑vision modalities supported
Best for
- Vision‑based QA
- Code generation with tool calls
- Procedural content creation
Who it’s for. Developers and researchers needing a vision‑enabled language model with strong reasoning and agentic capabilities. The model is suitable for applications that benefit from verified answers and structured output.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 10.1 GB | 11.2 GB | Too big | Get file → | |
| — | 13.4 GB | 14.5 GB | Too big | Get file → | |
| — | 13.4 GB | 14.6 GB | Too big | Get file → | |
| — | 21.2 GB | 22.3 GB | Too big | Get file → | |
| — | 24.7 GB | 25.9 GB | Too big | Get file → | |
| — | 28.8 GB | 30.0 GB | Too big | Get file → | |
| — | 36.9 GB | 38.1 GB | Too big | Get file → |
The available GGUF files range from 10.06 GB to 36.9 GB. For 8 GB VRAM, the 10.06 GB file is the smallest option; it will require approximately 11.2 GB of memory at 8 k context. For 12 GB VRAM, the 13.36 GB file uses about 14.5 GB of memory. Larger VRAM allows the 21.17 GB or 24.73 GB files, which need roughly 22.3 GB and 25.9 GB respectively. Memory estimates are approximate.
What GPU do you need for Deepwen 3.6?
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 the main file (10.1 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (13.4 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (28.8 GB file, about 30.0 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (36.9 GB file, about 38.1 GB in use).
Which Deepwen 3.6 quant should you choose?
If memory is tight, the smallest file is the first one in the table at 10.1 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 Deepwen 3.6
How much VRAM does Deepwen 3.6 need?
About 22.3 GB at its main file 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 Deepwen 3.6 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 Deepwen 3.6 GGUF?
It depends on the quant: file is 10.1 GB, file is 13.4 GB, file is 13.4 GB, file is 21.2 GB, file is 24.7 GB, file is 28.8 GB and 1 more.
What context length does Deepwen 3.6 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 Deepwen 3.6 GGUF?
The files are on Hugging Face in the quimmedes/Deepwen-3.6 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Deepwen 3.6 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 Deepwen 3.6 on 8 GB VRAM?
The smallest GGUF file is 10.06 GB and requires about 11.2 GB of memory at 8 k context, so 8 GB VRAM is insufficient.
Does Deepwen 3.6 support multiple languages?
No language list is provided; the model is not explicitly limited to any language.
Is Deepwen 3.6 licensed for commercial use?
The model is released under the apache‑2.0 license, which permits commercial use.