Tongyi DeepResearch 30B A3B needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 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 30 billion‑parameter agentic LLM with 3 billion active parameters per token
Tongyi DeepResearch 30B A3B is a 30 billion‑parameter model built on the qwen3moe architecture. It activates only 3 billion parameters per token, enabling efficient long‑horizon reasoning. The model supports a 131 072‑token context window and is released under Apache‑2.0.
Good at
- Long‑horizon reasoning
- Agentic search tasks
- Large context handling
Limits
- Requires high VRAM for full precision
- No vision support
- Large model size limits deployment on low‑end hardware
Best for
- Agentic search pipelines
- Complex multi‑step reasoning
- Research on long‑context LLMs
Who it’s for. Researchers and developers needing a large, agentic language model for deep information‑seeking tasks. The model is suitable for environments that can accommodate its memory footprint and support the qwen3moe architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ2_XXS | 7.6 GB | 8.9 GB | Too big | Get file → | |
| IQ2_XS | 8.7 GB | 10.0 GB | Too big | Get file → | |
| IQ2_S | 8.7 GB | 10.0 GB | Too big | Get file → | |
| IQ2_M | 9.9 GB | 11.2 GB | Too big | Get file → | |
| Q2_K | 10.9 GB | 12.2 GB | Too big | Get file → | |
| Q2_K_L | 11.2 GB | 12.5 GB | Too big | Get file → | |
| IQ3_XXS | 12.2 GB | 13.5 GB | Too big | Get file → | |
| IQ3_XS | 12.7 GB | 14.0 GB | Too big | Get file → | |
| Q3_K_S | 13.4 GB | 14.7 GB | Too big | Get file → | |
| IQ3_M | 14.1 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_M | 14.1 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 15.9 GB | Too big | Get file → | |
| Q3_K_XL | 14.9 GB | 16.2 GB | Too big | Get file → | |
| IQ4_XS | 16.5 GB | 17.8 GB | Too big | Get file → | |
| IQ4_NL | 17.4 GB | 18.7 GB | Too big | Get file → | |
| Q4_0 | 17.6 GB | 18.9 GB | Too big | Get file → | |
| Q4_K_S | 18.0 GB | 19.3 GB | Too big | Get file → | |
| Q4_K_M | 18.6 GB | 19.9 GB | Too big | Get file → | |
| Q4_K_L | 18.9 GB | 20.2 GB | Too big | Get file → | |
| Q4_1 | 19.2 GB | 20.5 GB | Too big | Get file → | |
| Q5_K_S | 21.1 GB | 22.4 GB | Too big | Get file → | |
| Q5_K_M | 21.7 GB | 23.0 GB | Too big | Get file → | |
| Q5_K_L | 21.9 GB | 23.2 GB | Too big | Get file → | |
| Q6_K | 25.1 GB | 26.4 GB | Too big | Get file → | |
| Q6_K_L | 25.3 GB | 26.6 GB | Too big | Get file → | |
| Q8_0 | 32.5 GB | 33.8 GB | Too big | Get file → | |
| BF16 | 61.1 GB (2 parts) | 62.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (7.57 GB) or IQ2_XS (8.66 GB). With 16 GB VRAM, IQ4_K_M (18.63 GB) or Q4_K_L (18.86 GB) are appropriate. For 32 GB VRAM, Q8_0 (32.48 GB) or BF16 shards (61.1 GB total) can be used, noting the split into two shards.
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 IQ2_M (9.9 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (14.6 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_L (21.9 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_L (25.3 GB file, about 26.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (32.5 GB file, about 33.8 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 18.6 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
Source
Frequently asked questions about Tongyi DeepResearch 30B A3B
How much VRAM does Tongyi DeepResearch 30B A3B need?
About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 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, IQ2_XXS is 7.6 GB, IQ2_XS is 8.7 GB, IQ2_S is 8.7 GB, IQ2_M is 9.9 GB, Q2_K is 10.9 GB and 22 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 bartowski/Alibaba-NLP_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?
Yes, using the IQ2_XXS or IQ2_XS quantizations, which require about 8–9 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model has no vision capabilities and is text‑only.
What license applies to this model?
The model is released under the Apache‑2.0 license.