Qwen3.6 35B A3B DFlash needs about 0.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB (Q4_K_M) to 1.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.
Qwen3.6 35B A3B DFlash – a lightweight speculative decoding drafter
Qwen3.6 35B A3B DFlash is a 0.474 billion‑parameter model designed for use with the llama.cpp dflash fork. It supports reasoning and tools and is released under the MIT license. The model is optimized for speculative decoding with a block diffusion drafter.
Good at
- Reasoning tasks
- Tool usage
- Speculative decoding
Limits
- No vision support
- Limited to 262144 context tokens
- Requires a drafter partner
Best for
- Agentic workflows
- Long‑context generation
- Parallel token drafting
Who it’s for. Developers building agentic or long‑context applications who need a lightweight drafter. The model is suitable for integration with llama.cpp or vLLM setups that support speculative decoding.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| BF16 | 1.0 GB | 1.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.29 GB file, ~0.9 GB VRAM). For 12 GB VRAM, Q6_K (0.4 GB file, ~1 GB VRAM) is suitable. For 16 GB VRAM, Q8_0 (0.51 GB file, ~1.1 GB VRAM) provides higher precision.
What GPU do you need for Qwen3.6 35B A3B DFlash?
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: the best quant that fits is BF16 (1.0 GB file, about 1.6 GB in use).
Which Qwen3.6 35B A3B DFlash quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 35B A3B DFlash: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.5 GB, about 1.8 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 DFlash
How much VRAM does Qwen3.6 35B A3B DFlash need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 DFlash on an 8 GB GPU?
Yes, with BF16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.6 35B A3B DFlash GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, Q6_K is 0.4 GB, Q8_0 is 0.5 GB, BF16 is 1.0 GB.
What context length does Qwen3.6 35B A3B DFlash support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.5 GB at 32K.
Where can I download Qwen3.6 35B A3B DFlash GGUF?
The files are on Hugging Face in the abhinand/Qwen3.6-35B-A3B-DFlash-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 DFlash use?
Hugging Face lists the license as mit. 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 DFlash on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 0.9 GB VRAM at 8k context, fitting within 8 GB.
Does this model support vision?
No, the model does not include vision capabilities.
What license does the model use?
The model is released under the MIT license.