Qwen3.6 35B A3B DFlash needs about 1.1 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.
Qwen3.6 35B A3B DFlash – lightweight draft model for speculative decoding
Qwen3.6 35B A3B DFlash is a DFlash draft model built on Qwen/Qwen3.6-35B-A3B. It is quantized to Q8_0 and designed to work with a target model in a speculative decoding server. The model supports a 40960 token context length and is licensed under apache-2.0.
Good at
- Speculative decoding draft
- Long‑context support
- High throughput with DFlash
Limits
- No vision support
- Requires a target model
- Large VRAM needed for full performance
Best for
- Serving high‑concurrency inference
- Speeding up autoregressive generation
- Optimizing draft paths in SGLang
Who it’s for. Developers building inference servers that support DFlash speculative decoding. The model is intended to be paired with a target model and used in a server environment such as SGLang.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.4 GB | 1.1 GB | Fits | Get file → |
The only available quant is Q8_0, file size 0.42 GB. It requires approximately 1.1 GB of VRAM at 8 k context. For lower VRAM budgets, no other quant is available in the file list.
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 Q8_0 (0.4 GB file, about 1.1 GB in use).
Which Qwen3.6 35B A3B DFlash quant should you choose?
Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
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 1.1 GB at Q8_0 with an 8K context window. That is the 0.4 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 Q8_0: the 0.4 GB file needs about 1.1 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: Q8_0 is 0.4 GB.
What context length does Qwen3.6 35B A3B DFlash support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.8 GB at 32K.
Where can I download Qwen3.6 35B A3B DFlash GGUF?
The files are on Hugging Face in the magnitudedev/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 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 Qwen3.6 35B A3B DFlash on 8 GB VRAM?
The Q8_0 quant uses about 1.1 GB of VRAM at 8 k context, so 8 GB VRAM is sufficient for this model alone, but additional memory will be needed for the target model and server overhead.
Does this model support vision tasks?
No, the model has no vision capabilities and is intended for language generation only.
What license applies to this model?
The model is released under the apache-2.0 license.