QW

Qwen3 MOE 2x8B TNG Deckard Beta 16B

QwenGGUF by mradermacherUpdated 2025-12-06
Download on Hugging Face
Parameters13.4B
Context256K
Layers72
Architectureqwen3moe
Smallest quant0.0 GB
Quick answer

Qwen3 MOE 2x8B TNG Deckard Beta 16B needs about 11.1 GB of memory at Q4_K_M (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 11.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.7 GB.

Qwen3 MOE 2x8B TNG Deckard Beta 16B – 13.4B parameter mixture of experts

Qwen3 MOE 2x8B TNG Deckard Beta 16B is a 13.4B parameter model with a mixture of experts architecture. It supports coding, reasoning, and tool usage. The model is trained on a context of 262144 tokens and released under the Apache‑2.0 license.

Good at

  • Coding tasks
  • Logical reasoning
  • Tool integration

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • Requires GGUF format

Best for

  • Developers building code assistants
  • Researchers testing reasoning models
  • Tool‑enabled chatbot developers

Who it’s for. This model is suited for developers and researchers who need a large, expert‑based language model for code generation, logical reasoning, and tool‑driven applications. It is ideal for those with sufficient GPU memory to run higher‑quality quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.9 GB
Fits Get file →
IQ1_S3.0 GB 6.0 GB
Fits Get file →
IQ1_M3.3 GB 6.2 GB
Fits Get file →
IQ2_XXS3.8 GB 6.7 GB
Fits Get file →
IQ2_XS4.1 GB 7.0 GB
Fits Get file →
IQ2_S4.3 GB 7.2 GB
Tight Get file →
IQ2_M4.7 GB 7.6 GB
Tight Get file →
Q2_K_S4.8 GB 7.7 GB
Tight Get file →
Q2_K5.1 GB 8.0 GB
Too big Get file →
IQ3_XXS5.3 GB 8.2 GB
Too big Get file →
IQ3_XS5.7 GB 8.6 GB
Too big Get file →
Q3_K_S5.9 GB 8.8 GB
Too big Get file →
IQ3_S6.0 GB 8.9 GB
Too big Get file →
IQ3_M6.1 GB 9.0 GB
Too big Get file →
Q3_K_M6.6 GB 9.5 GB
Too big Get file →
Q3_K_L7.1 GB 10.0 GB
Too big Get file →
IQ4_XS7.3 GB 10.2 GB
Too big Get file →
IQ4_NL7.7 GB 10.6 GB
Too big Get file →
Q4_07.7 GB 10.6 GB
Too big Get file →
Q4_K_S7.7 GB 10.6 GB
Too big Get file →
Q4_K_M8.1 GB 11.1 GB
Too big Get file →
Q4_18.5 GB 11.4 GB
Too big Get file →
Q5_K_S9.3 GB 12.2 GB
Too big Get file →
Q5_K_M9.5 GB 12.5 GB
Too big Get file →
Q6_K11.0 GB 13.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 8.15 GB, estimated 11.1 GB memory). For 12 GB VRAM, Q5_K_M (9.54 GB, 12.5 GB memory) is suitable. For 16 GB VRAM, Q6_K (11.02 GB, 13.9 GB memory) offers the best quality.

What GPU do you need for Qwen3 MOE 2x8B TNG Deckard Beta 16B?

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 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ1_S (3.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K (5.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (8.5 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.0 GB file, about 13.9 GB in use).

Which Qwen3 MOE 2x8B TNG Deckard Beta 16B quant should you choose?

Q4_K_M is the usual starting point for Qwen3 MOE 2x8B TNG Deckard Beta 16B: it balances file size and quality well. Here it is a 8.1 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

Architectureqwen3moe
Parameters13.4B (approximate, mixture of experts)
Layers72
Trained context262,144 tokens
KV cache (fp16)288 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)617
Last updated2025-12-06

Frequently asked questions about Qwen3 MOE 2x8B TNG Deckard Beta 16B

How much VRAM does Qwen3 MOE 2x8B TNG Deckard Beta 16B need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.1 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 MOE 2x8B TNG Deckard Beta 16B on an 8 GB GPU?

Yes, with Q2_K: the 5.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 MOE 2x8B TNG Deckard Beta 16B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.0 GB, IQ1_M is 3.3 GB, IQ2_XXS is 3.8 GB, IQ2_XS is 4.1 GB, IQ2_S is 4.3 GB and 19 more.

What context length does Qwen3 MOE 2x8B TNG Deckard Beta 16B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.7 GB at 32K.

Where can I download Qwen3 MOE 2x8B TNG Deckard Beta 16B GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-MOE-2x8B-TNG-Deckard-Beta-16B-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 Qwen3 MOE 2x8B TNG Deckard Beta 16B 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 11.1 GB memory at 8k context, which fits within 8 GB VRAM with some overhead.

Does this model support vision?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →