Marco DeepResearch 8B needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.1 GB (IQ1_S) to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Marco DeepResearch 8B – an 8B‑scale deep research agent
Marco DeepResearch 8B is a Qwen3‑based model with 8.19 billion parameters. It performs multi‑step reasoning and tool use for open‑ended investigations. The model is optimized with a verification‑centric framework and supports up to 131072 context tokens.
Good at
- Multi‑step reasoning
- Tool‑based web research
- Verification‑driven inference
Limits
- No vision support
- Requires at least 8 k context for memory estimates
- Apache‑2.0 license
Best for
- Research assistants
- Automated web data extraction
- Tool‑enabled LLM workflows
Who it’s for. Developers building research agents or tool‑enabled applications. The model is suitable for users who need robust reasoning and verification in a compact 8B footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ1_M | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.5 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XS | 2.7 GB | 4.4 GB | Fits | Get file → | |
| IQ2_S | 2.9 GB | 4.6 GB | Fits | Get file → | |
| IQ2_M | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_S | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.4 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XS | 3.6 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 4.4 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 4.8 GB | 6.5 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_S (2.86 GB file, 4.6 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (5.03 GB file, 6.7 GB memory) offers a good balance. For 16 GB VRAM, Q6_K (6.73 GB file, 8.4 GB memory) gives the best quality.
What GPU do you need for Marco DeepResearch 8B?
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 IQ1_M (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.4 GB in use).
Which Marco DeepResearch 8B quant should you choose?
Q4_K_M is the usual starting point for Marco DeepResearch 8B: it balances file size and quality well. Here it is a 5.0 GB file.
If memory is tight, the smallest file is IQ1_S at 2.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Marco DeepResearch 8B
How much VRAM does Marco DeepResearch 8B need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Marco DeepResearch 8B on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Marco DeepResearch 8B GGUF?
It depends on the quant: IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB, IQ2_M is 3.1 GB and 18 more.
What context length does Marco DeepResearch 8B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Marco DeepResearch 8B GGUF?
The files are on Hugging Face in the ATH-MaaS/Marco-DeepResearch-8B-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 Marco DeepResearch 8B 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 Marco DeepResearch 8B on 8 GB VRAM?
Yes, the IQ2_S quantization uses 2.86 GB file size and requires approximately 4.6 GB memory at 8 k context.
Does the model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.