TO

Tongyi-DeepResearch-30B-A3B

TongyiGGUF by MungertUpdated 2025-11-03
Download on Hugging Face
Parameters30.5B
Context128K
Layers48
Architectureqwen3moe
Smallest quant0.1 GB
Quick answer

Tongyi-DeepResearch-30B-A3B needs about 20.3 GB of memory at Q4_K_M (a 19.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 0.1 GB to 61.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Tongyi-DeepResearch-30B-A3B – a 30B MoE model for long‑horizon tasks

Tongyi-DeepResearch-30B-A3B is a 30.5 billion‑parameter model with 3 billion active parameters per token. It is trained on 131072 context tokens and supports long‑horizon, deep information‑seeking tasks. The model is released under the apache‑2.0 license.

Good at

  • Long‑horizon reasoning
  • Agentic search
  • Deep information‑seeking

Limits

  • No vision support
  • Requires large VRAM for higher‑bit quantizations
  • Limited to 131072 context tokens

Best for

  • Research on agentic LLMs
  • Long‑form content generation
  • Complex reasoning workflows

Who it’s for. Researchers and developers needing a large‑scale MoE model for advanced reasoning tasks. The model is suitable for users with sufficient GPU memory to run higher‑bit quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ1_S9.1 GB 10.4 GB
Too big Get file →
IQ2_XXS9.8 GB 11.1 GB
Too big Get file →
IQ1_M10.0 GB 11.3 GB
Too big Get file →
IQ2_XS11.0 GB 12.3 GB
Too big Get file →
IQ2_S11.0 GB 12.3 GB
Too big Get file →
IQ2_M11.5 GB 12.8 GB
Too big Get file →
Q2_K_S11.9 GB 13.2 GB
Too big Get file →
Q2_K_M12.0 GB 13.3 GB
Too big Get file →
IQ3_XXS13.7 GB 15.0 GB
Too big Get file →
IQ3_XS13.8 GB 15.1 GB
Too big Get file →
IQ3_M15.4 GB 16.7 GB
Too big Get file →
Q3_K_S15.8 GB 17.1 GB
Too big Get file →
Q3_K_M15.8 GB 17.2 GB
Too big Get file →
IQ4_XS16.5 GB 17.8 GB
Too big Get file →
IQ4_NL17.2 GB 18.5 GB
Too big Get file →
Q4_017.5 GB 18.8 GB
Too big Get file →
Q4_K_S18.2 GB 19.5 GB
Too big Get file →
Q4_K_M19.0 GB 20.3 GB
Too big Get file →
Q4_119.2 GB 20.5 GB
Too big Get file →
Q5_021.3 GB 22.6 GB
Too big Get file →
Q5_K_M22.5 GB 23.8 GB
Too big Get file →
Q5_123.1 GB 24.4 GB
Too big Get file →
Q6_K_M25.2 GB 26.5 GB
Too big Get file →
Q8_032.5 GB 33.8 GB
Too big Get file →
F1638.7 GB 40.0 GB
Too big Get file →
BF1661.1 GB (2 parts) 62.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 9.09 GB, memory 10.4 GB). For 12 GB VRAM, IQ2_S (file size 11.01 GB, memory 12.3 GB). For 20 GB VRAM, Q4_K_M (file size 19.03 GB, memory 20.3 GB). Estimates are approximate.

What GPU do you need for Tongyi-DeepResearch-30B-A3B?

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 (0.1 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (10.0 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.8 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (22.5 GB file, about 23.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_M (25.2 GB file, about 26.5 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (38.7 GB file, about 40.0 GB in use).

Which Tongyi-DeepResearch-30B-A3B quant should you choose?

Q4_K_M is the usual starting point for Tongyi-DeepResearch-30B-A3B: it balances file size and quality well. Here it is a 19.0 GB file.

The Q8_0 file is 32.5 GB, about 1.7 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.

If memory is tight, the smallest file is the first one in the table at 0.1 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
Parameters30.5B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context131,072 tokens
KV cache (fp16)96 KB per token

Source

Quantized byMungert
FamilyTongyi
Licenseapache-2.0
Downloads (HF)1,574
Last updated2025-11-03

Frequently asked questions about Tongyi-DeepResearch-30B-A3B

How much VRAM does Tongyi-DeepResearch-30B-A3B need?

About 20.3 GB at Q4_K_M with an 8K context window. That is the 19.0 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 Tongyi-DeepResearch-30B-A3B on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tongyi-DeepResearch-30B-A3B GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 9.1 GB, IQ2_XXS is 9.8 GB, IQ1_M is 10.0 GB, IQ2_XS is 11.0 GB, IQ2_S is 11.0 GB and 21 more.

What context length does Tongyi-DeepResearch-30B-A3B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Tongyi-DeepResearch-30B-A3B GGUF?

The files are on Hugging Face in the Mungert/Tongyi-DeepResearch-30B-A3B-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 Tongyi-DeepResearch-30B-A3B 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 Tongyi-DeepResearch-30B-A3B on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 10.4 GB of VRAM at 8 k context.

Does the model support vision tasks?

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 Mungert

All by Mungert →

More Tongyi models

All Tongyi →

Other medium models

All medium models →