FL

Q3.6 27B DS v4 Flash DA

FlashGGUF by mradermacherUpdated 2026-06-02
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Q3.6 27B DS v4 Flash DA needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Q3.6-27B-DS-v4-Flash-DA: 27B reasoning‑focused model

Q3.6-27B-DS-v4-Flash-DA is a 27B parameter model built on Qwen3.6. It is fine‑tuned with DeepSeek V4 Flash distilled reasoning traces and ablation‑based training to enhance reasoning depth while reducing internal refusal behaviors.

Good at

  • Deep multi‑step reasoning
  • Instruction following with reasoning
  • Long‑context coherence

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • Experimental model may generate artifacts

Best for

  • Research on reasoning and alignment
  • Complex chain‑of‑thought tasks
  • Multi‑GPU inference setups

Who it’s for. Researchers and developers needing advanced reasoning capabilities in a local deployment. The model is intended for research and learning purposes and may produce unrestricted content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.1 GB 9.8 GB
Too big Get file →
IQ1_M7.6 GB 10.3 GB
Too big Get file →
IQ2_XXS8.4 GB 11.1 GB
Too big Get file →
IQ2_XS9.1 GB 11.7 GB
Too big Get file →
IQ2_S9.4 GB 12.0 GB
Too big Get file →
IQ2_M10.0 GB 12.7 GB
Too big Get file →
Q2_K_S10.2 GB 12.9 GB
Too big Get file →
Q2_K10.7 GB 13.4 GB
Too big Get file →
IQ3_XXS11.2 GB 13.8 GB
Too big Get file →
IQ3_XS12.0 GB 14.6 GB
Too big Get file →
Q3_K_S12.1 GB 14.7 GB
Too big Get file →
IQ3_S12.4 GB 15.1 GB
Too big Get file →
IQ3_M12.6 GB 15.2 GB
Too big Get file →
Q3_K_M13.3 GB 15.9 GB
Too big Get file →
Q3_K_L14.3 GB 17.0 GB
Too big Get file →
IQ4_XS15.1 GB 17.7 GB
Too big Get file →
Q4_015.5 GB 18.2 GB
Too big Get file →
Q4_K_S15.6 GB 18.2 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q4_117.1 GB 19.7 GB
Too big Get file →
Q5_K_S18.7 GB 21.3 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 7.15 GB, memory 9.8 GB). For 12 GB VRAM, IQ2_S (file size 9.36 GB, memory 12 GB). For 24 GB VRAM, Q6_K (file size 22.08 GB, memory 24.7 GB). Estimates are approximate.

What GPU do you need for Q3.6 27B DS v4 Flash DA?

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 the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (9.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.1 GB file, about 24.7 GB in use).

Which Q3.6 27B DS v4 Flash DA quant should you choose?

Q4_K_M is the usual starting point for Q3.6 27B DS v4 Flash DA: it balances file size and quality well. Here it is a 16.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architectureqwen35
Parameters27B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyFlash
Licenseapache-2.0
Downloads (HF)2,293
Last updated2026-06-02

Frequently asked questions about Q3.6 27B DS v4 Flash DA

How much VRAM does Q3.6 27B DS v4 Flash DA need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Q3.6 27B DS v4 Flash DA on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Q3.6 27B DS v4 Flash DA GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.1 GB, IQ1_M is 7.6 GB, IQ2_XXS is 8.4 GB, IQ2_XS is 9.1 GB, IQ2_S is 9.4 GB and 18 more.

What context length does Q3.6 27B DS v4 Flash DA support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Q3.6 27B DS v4 Flash DA GGUF?

The files are on Hugging Face in the mradermacher/Q3.6-27B-DS-v4-Flash-DA-i1-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 Q3.6 27B DS v4 Flash DA 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 Q3.6-27B-DS-v4-Flash-DA on 8 GB VRAM?

Use the IQ1_S quant, which requires about 9.8 GB of VRAM at 8 k context.

Does this model support vision?

No, it is a text‑only model.

Is the model safe for production use?

It is experimental and may generate unrestricted content; use with caution.

Other GGUFs of Q3.6-27B-DS-v4-Flash-DA

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Flash models

All Flash →

Other medium models

All medium models →