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 12 quants, from 3.3 GB (Q2_K) to 16.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Marco DeepResearch 8B – an 8B Qwen3‑based research agent with tool use
Marco DeepResearch 8B is a Qwen3‑based deep research agent with 8.19 billion parameters. It performs multi‑step reasoning and tool‑based web research. The model is released under Apache‑2.0 and supports reasoning and tools.
Good at
- Multi‑step reasoning
- Tool‑based web research
- Verification‑centric outputs
Limits
- No vision support
- Requires 8 k context for estimates
- No other modalities
Best for
- Research assistants
- Data‑driven Q&A
- Tool‑enabled browsing
Who it’s for. Developers building research assistants or data‑driven applications that need iterative web search and verification. The model is suitable for users with access to a compatible inference engine such as llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.5 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_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 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 → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| F16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 5.03 GB, estimated 6.7 GB memory). For 12 GB VRAM use Q5_K_M (5.85 GB, 7.6 GB). For 16 GB VRAM use Q6_K (6.73 GB, 8.4 GB). Higher quality Q8_0 or Q6_K requires more memory.
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: no quant fits at an 8K context.
- 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 Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.4 GB file, about 18.1 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.
The Q8_0 file is 8.7 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 Q2_K at 3.3 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: Q2_K is 3.3 GB, Q3_K_S is 3.8 GB, Q3_K_M is 4.1 GB, Q3_K_L is 4.4 GB, IQ4_XS is 4.6 GB, Q4_K_S is 4.8 GB and 6 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-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, use the Q4_K_M quantization which estimates 6.7 GB memory at 8 k context.
Does the model support image inputs?
No, the model does not support vision or image modalities.
What license applies to the model?
The model is released under the Apache‑2.0 license.