QW

Qwen3.6 35B A3B DFlash2

QwenGGUF by aminyaUpdated 2026-10-09
Download on Hugging Face
Parameters526M
Context256K
Layers6
Architecturedflash
Smallest quant0.3 GB
Quick answer

Qwen3.6 35B A3B DFlash2 needs about 1.0 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 3 quants, from 0.3 GB (Q4_K_M) to 1.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.

Qwen3.6 35B A3B DFlash2 – a draft model for speculative decoding

Qwen3.6 35B A3B DFlash2 is a block‑diffusion drafter that works with a compatible Qwen3.6‑35B‑A3B target model. It predicts a block of tokens in one pass and selects a coherent path for verification. The model is released under Apache‑2.0.

Good at

  • Speculative decoding draft
  • Block‑diffusion token prediction
  • Compatible with Qwen3.6‑35B‑A3B

Limits

  • Not a standalone chat model
  • Requires a compatible target model
  • No vision support

Best for

  • Speeding up Qwen3.6 inference
  • Reducing decoding workload
  • Testing speculative decoding setups

Who it’s for. Developers building speculative decoding pipelines with Qwen3.6‑35B‑A3B. The model is useful for research and production environments that need a lightweight draft model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.3 GB 1.0 GB
Fits Get file →
Q8_00.6 GB 1.3 GB
Fits Get file →
BF161.1 GB 1.8 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M file (0.31 GB, ~1 GB memory at 8 k context). For 16 GB VRAM, the Q8_0 file (0.57 GB, ~1.3 GB memory) is suitable. For larger memory budgets, the BF16 file (1.06 GB, ~1.8 GB memory) offers higher precision.

What GPU do you need for Qwen3.6 35B A3B DFlash2?

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 (1.1 GB file, about 1.8 GB in use).

Which Qwen3.6 35B A3B DFlash2 quant should you choose?

Q4_K_M is the usual starting point for Qwen3.6 35B A3B DFlash2: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.6 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

Architecturedflash
Parameters526M
Layers6
Trained context262,144 tokens
KV cache (fp16)24 KB per token

Source

Quantized byaminya
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,716
Last updated2026-10-09

Frequently asked questions about Qwen3.6 35B A3B DFlash2

How much VRAM does Qwen3.6 35B A3B DFlash2 need?

About 1.0 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 DFlash2 on an 8 GB GPU?

Yes, with BF16: the 1.1 GB file needs about 1.8 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 DFlash2 GGUF?

It depends on the quant: Q4_K_M is 0.3 GB, Q8_0 is 0.6 GB, BF16 is 1.1 GB.

What context length does Qwen3.6 35B A3B DFlash2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.8 GB at 32K.

Where can I download Qwen3.6 35B A3B DFlash2 GGUF?

The files are on Hugging Face in the aminya/Qwen3.6-35B-A3B-DFlash2-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 DFlash2 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 DFlash2 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 1 GB of VRAM at 8 k context, which fits in 8 GB.

Does this model support vision tasks?

No, it is a language draft model and does not provide vision capabilities.

What license applies to this model?

The model is released under the Apache License 2.0.

Other GGUFs of Qwen3.6-35B-A3B-DFlash2

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →