AIDC-AI/Marco-DeepResearch-8B-i1-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: AIDC-AI/Marco-DeepResearch-8B-i1-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-11 18:02:13 +08:00
commit 0111c888a9
27 changed files with 544 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
.gitattributes vendored Normal file
View File

@@ -0,0 +1,84 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Marco-DeepResearch-8B-i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

3
Marco-DeepResearch-8B-i1-IQ1_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:93012905a87efb21386451a35109f4fabc8b91a1ed6a0d4539379dcb5a7841ef
size 2256148160

3
Marco-DeepResearch-8B-i1-IQ1_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea85e59e2b504c6051dad40d72510908566cf6b6d4fd6295486f66ea5781cd57
size 2115770048

3
Marco-DeepResearch-8B-i1-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b759222ba7c119a32c8d267d0c6710b8e8a184b22817f70246262a2176867e34
size 3051914944

3
Marco-DeepResearch-8B-i1-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d4a072375992d3bd57e999b92b489f9099f3cd709f65b480df95cca0a75a9007
size 2864744128

3
Marco-DeepResearch-8B-i1-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb118bfdf9ba81d0e117c6eadd0e4448a84a35cbdf9cfd544ca1be26110f41a9
size 2696156864

3
Marco-DeepResearch-8B-i1-IQ2_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb4462c4880b6dbb197882310fd12f5628a2cf39902054ffc743509c4ae77c54
size 2490111680

3
Marco-DeepResearch-8B-i1-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8fa6d6dc992b5b6fab7a0f5fbac0709543992c50f3a9d18960d3d81f1fd3067
size 3896620736

3
Marco-DeepResearch-8B-i1-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:416ad849a2884bd01d054b20193af4daf052171b3eae023a66ffaf5947f61f3a
size 3789665984

3
Marco-DeepResearch-8B-i1-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5b9aac9fba35323be492b5b1ad771f1aaff85b4461664787086a9b995316cbf0
size 3626874560

3
Marco-DeepResearch-8B-i1-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c0a16fee64a6e52b3cb4b69395a2bcf928f9674e73f10bb53e7e7b346711289c
size 3369633472

3
Marco-DeepResearch-8B-i1-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:059711ee86122724222dcbacb972159a836ae4e5adf363a927e6e0ff5d9b6ece
size 4793624256

3
Marco-DeepResearch-8B-i1-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:164afba5607b90800da45dd5ee5db21c2e11fe6b269a30426f588907ac628290
size 4561839808

3
Marco-DeepResearch-8B-i1-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:948edabb2e39c4a05d52584679a605cd86f93c17753e870a9654ad8a3560c936
size 3281733312

3
Marco-DeepResearch-8B-i1-Q2_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:268300f2360fe7b62b5b239a3ad4f387e8dbf8ca3fe3d1603b4621f28d690e16
size 3083552448

3
Marco-DeepResearch-8B-i1-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5a3e11d48a9b090433e4590ecd3a5b9fd857df49c3f6c1d688a4e206788f48f2
size 4431394496

3
Marco-DeepResearch-8B-i1-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:34895488be27b1362866a70335deeaef467ca1dd9993c4fec6e2b9f13abb01c9
size 4124161728

3
Marco-DeepResearch-8B-i1-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9fc0f0c91d1d2541589b8ad08684f2273de89ef6764671737868f02a1b7aa1f1
size 3769611968

3
Marco-DeepResearch-8B-i1-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dedfbd4682ee9ac59267ffc5365f75919b4db2188b30d0adb9bef8ad15217b43
size 4787332800

3
Marco-DeepResearch-8B-i1-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c96445892fa3f4ecc3bb639fde9b86836172cfb65cbaf903043fa7288d1b06b0
size 5247755968

3
Marco-DeepResearch-8B-i1-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:49cc9062a59172969f2a28e2d9df5ff25d61e2456307b12b7725050b8b184405
size 5027784384

3
Marco-DeepResearch-8B-i1-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9fabcadedabf31eb619a862f704a0cf995f6e18601cdffec2916ac04b332823
size 4802012864

3
Marco-DeepResearch-8B-i1-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0260c682dfa5d839d2ff7f4d498acc7087223ddd3a4081fb0bab7fc3fa98eb7e
size 5851113152

3
Marco-DeepResearch-8B-i1-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85bc08255120a6e097c1bb2d1fe8fede6fd4db25ee911f3a4537a24fca9553c8
size 5720762048

3
Marco-DeepResearch-8B-i1-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2bb7fefac8f601c77844a9df8b66d9f609e3391ff4a19eb03a86094b288c632d
size 6725899968

387
README.md Normal file
View File

@@ -0,0 +1,387 @@
---
license: apache-2.0
language:
- en
- zh
base_model: AIDC-AI/Marco-DeepResearch-8B
tags:
- gguf
- quantized
- imatrix
- importance-matrix
- deep-research
- agent
- information-seeking
- web-search
- verification
- react
- llama-cpp
- qwen3
pipeline_tag: text-generation
model-index:
- name: Marco-DeepResearch-8B-imatrix-GGUF
results:
- task:
type: question-answering
name: BrowseComp
dataset:
name: BrowseComp
type: browsecomp
metrics:
- type: accuracy
value: 31.4
name: Accuracy
- task:
type: question-answering
name: BrowseComp-ZH
dataset:
name: BrowseComp-ZH
type: browsecomp-zh
metrics:
- type: accuracy
value: 47.1
name: Accuracy
- task:
type: question-answering
name: GAIA (text-only)
dataset:
name: GAIA
type: gaia
metrics:
- type: accuracy
value: 69.9
name: Accuracy
- task:
type: question-answering
name: xBench-DeepSearch-2505
dataset:
name: xBench-DeepSearch-2505
type: xbench-deepsearch
metrics:
- type: accuracy
value: 82.0
name: Accuracy
- task:
type: question-answering
name: WebWalkerQA
dataset:
name: WebWalkerQA
type: webwalkerqa
metrics:
- type: accuracy
value: 69.6
name: Accuracy
---
# Marco-DeepResearch-8B-imatrix-GGUF
Importance-matrix (imatrix) GGUF quantized versions of [AIDC-AI/Marco-DeepResearch-8B](https://huggingface.co/AIDC-AI/Marco-DeepResearch-8B) for use with [llama.cpp](https://github.com/ggerganov/llama.cpp) and compatible inference engines.
For standard quantizations without importance matrix, see [Marco-DeepResearch-8B-GGUF](https://huggingface.co/AIDC-AI/Marco-DeepResearch-8B-GGUF).
## About the Model
**Marco DeepResearch** is an efficient 8B-scale deep research agent developed by **Alibaba International Digital Commerce (AIDC-AI)**, based on [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B). It autonomously conducts open-ended investigations by integrating complex information retrieval with multi-step reasoning across diverse web sources. The model uses tools (`search`, `visit`) for iterative web research with built-in verification.
Under a maximum budget of 600 tool calls, Marco DeepResearch significantly outperforms other 8B-scale agents and surpasses or approaches several 30B-scale agents on challenging benchmarks.
## What is Importance Matrix (imatrix) Quantization?
Standard quantization treats all model weights equally when reducing precision. Importance matrix quantization improves on this by first profiling the model with calibration data to determine which weights matter most for output quality. During quantization, more important weights are preserved with higher precision while less critical weights are compressed more aggressively.
The result is **significantly better quality at low bit rates** (Q3, Q2, IQ3, IQ2, IQ1) compared to standard quantization. At higher bit rates (Q5, Q6), the difference is minimal. If you need to run at 3 bits or below, imatrix quants are strongly recommended.
**Calibration data:** WikiText-2
## Included Files
The `imatrix.dat` file (5.1 MB) is included in this repository. You can use it with llama.cpp's `llama-quantize` to create your own custom quantizations from a full-precision GGUF.
## Available Quantizations
| Filename | Quant Type | Size | Description |
|---|---|---|---|
| Marco-DeepResearch-8B-i1-Q6_K.gguf | Q6_K | 6.3 GB | Very high quality. Near-lossless. |
| Marco-DeepResearch-8B-i1-Q5_K_M.gguf | Q5_K_M | 5.5 GB | High quality. **Recommended for most users.** |
| Marco-DeepResearch-8B-i1-Q5_K_S.gguf | Q5_K_S | 5.4 GB | High quality. Slightly smaller than Q5_K_M. |
| Marco-DeepResearch-8B-i1-Q4_1.gguf | Q4_1 | 4.9 GB | Good quality. Legacy 4-bit format. |
| Marco-DeepResearch-8B-i1-Q4_K_M.gguf | Q4_K_M | 4.7 GB | Good quality. **Best 4-bit option.** |
| Marco-DeepResearch-8B-i1-Q4_K_S.gguf | Q4_K_S | 4.5 GB | Good quality. Smaller than Q4_K_M. |
| Marco-DeepResearch-8B-i1-IQ4_NL.gguf | IQ4_NL | 4.5 GB | Good quality. Non-linear 4-bit quant. |
| Marco-DeepResearch-8B-i1-Q4_0.gguf | Q4_0 | 4.5 GB | Decent quality. Legacy 4-bit format. |
| Marco-DeepResearch-8B-i1-IQ4_XS.gguf | IQ4_XS | 4.3 GB | Decent quality. Smallest 4-bit variant. |
| Marco-DeepResearch-8B-i1-Q3_K_L.gguf | Q3_K_L | 4.2 GB | Moderate quality. imatrix helps noticeably here. |
| Marco-DeepResearch-8B-i1-Q3_K_M.gguf | Q3_K_M | 3.9 GB | Moderate quality. Good for memory-constrained setups. |
| Marco-DeepResearch-8B-i1-IQ3_M.gguf | IQ3_M | 3.7 GB | Moderate quality. Better than Q3_K_S at similar size. |
| Marco-DeepResearch-8B-i1-IQ3_S.gguf | IQ3_S | 3.6 GB | Lower quality. imatrix essential at this level. |
| Marco-DeepResearch-8B-i1-Q3_K_S.gguf | Q3_K_S | 3.6 GB | Lower quality. imatrix provides clear benefit. |
| Marco-DeepResearch-8B-i1-IQ3_XS.gguf | IQ3_XS | 3.4 GB | Lower quality. Aggressive compression. |
| Marco-DeepResearch-8B-i1-IQ3_XXS.gguf | IQ3_XXS | 3.2 GB | Low quality. For extreme memory constraints. |
| Marco-DeepResearch-8B-i1-Q2_K.gguf | Q2_K | 3.1 GB | Low quality. imatrix significantly helps. |
| Marco-DeepResearch-8B-i1-Q2_K_S.gguf | Q2_K_S | 2.9 GB | Very low quality. Experimental. |
| Marco-DeepResearch-8B-i1-IQ2_M.gguf | IQ2_M | 2.9 GB | Very low quality. Best option at ~2-bit. |
| Marco-DeepResearch-8B-i1-IQ2_S.gguf | IQ2_S | 2.7 GB | Very low quality. Heavy degradation expected. |
| Marco-DeepResearch-8B-i1-IQ2_XS.gguf | IQ2_XS | 2.6 GB | Extremely low quality. Research/testing only. |
| Marco-DeepResearch-8B-i1-IQ2_XXS.gguf | IQ2_XXS | 2.4 GB | Extremely low quality. Research/testing only. |
| Marco-DeepResearch-8B-i1-IQ1_M.gguf | IQ1_M | 2.2 GB | Minimal quality. Extreme compression research. |
| Marco-DeepResearch-8B-i1-IQ1_S.gguf | IQ1_S | 2.0 GB | Minimal quality. Maximum compression. |
### Choosing a Quantization
- **Best quality:** Q6_K or Q5_K_M — recommended if you have sufficient RAM/VRAM.
- **Best balance:** Q4_K_M — recommended for most users on consumer hardware.
- **Memory constrained:** Q3_K_M or IQ3_M — imatrix provides clear quality gains at this level.
- **Extreme constraints:** IQ2_M or IQ2_S — only viable with imatrix; expect significant quality loss.
- **Ultra-low (research):** IQ1_M / IQ1_S — extreme compression for experimentation.
### Creating Custom Quantizations
You can use the included `imatrix.dat` to create your own quants:
```bash
./llama-quantize --imatrix imatrix.dat \
Marco-DeepResearch-8B-f16.gguf \
Marco-DeepResearch-8B-i1-<QUANT_TYPE>.gguf \
<QUANT_TYPE>
```
## Usage
### llama.cpp
**CPU inference:**
```bash
./llama-cli -m Marco-DeepResearch-8B-i1-Q5_K_M.gguf \
-p "<your prompt>" \
-n 4096 \
--temp 0.7 --top-p 0.95 \
-t $(nproc)
```
**GPU-accelerated inference:**
```bash
./llama-cli -m Marco-DeepResearch-8B-i1-Q5_K_M.gguf \
-p "<your prompt>" \
-n 4096 \
--temp 0.7 --top-p 0.95 \
-ngl 99
```
**Server mode (OpenAI-compatible API):**
```bash
./llama-server -m Marco-DeepResearch-8B-i1-Q5_K_M.gguf \
--port 8080 \
-ngl 99 \
-c 32768
```
### Ollama
Create a `Modelfile`:
```
FROM ./Marco-DeepResearch-8B-i1-Q5_K_M.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.95
PARAMETER num_ctx 32768
```
Then:
```bash
ollama create marco-deepresearch -f Modelfile
ollama run marco-deepresearch
```
### Python (llama-cpp-python)
```python
from llama_cpp import Llama
llm = Llama(
model_path="Marco-DeepResearch-8B-i1-Q5_K_M.gguf",
n_ctx=32768,
n_gpu_layers=-1, # Use all GPU layers; set to 0 for CPU-only
)
output = llm(
"<your prompt>",
max_tokens=4096,
temperature=0.7,
top_p=0.95,
)
print(output["choices"][0]["text"])
```
### LM Studio
1. Download your desired quantization file (e.g., `Marco-DeepResearch-8B-i1-Q4_K_M.gguf`).
2. Open LM Studio and import the model file.
3. Configure generation settings: Temperature 0.7, Top-P 0.95.
4. Set context length to 32768 (or higher if your hardware allows).
5. Start chatting or use the local server API.
## Prompt Format
This model uses a structured prompt format with `<think>`, `<tool_call>`, and `<answer>` tags.
### System Prompt Template
```
You are an expert web researcher. Your task is to find accurate, complete answers through iterative search, extraction, and verification.
## Core Principles
1) Strategic Planning
- Decompose complex questions into targeted sub-tasks
- Choose the right tool for each step
- Refine your approach based on what you learn
2) Precise Execution
- Define clear objectives before using any tool
- Provide sufficient detail for accurate results
- Avoid vague or overly broad requests
3) Rigorous Verification
- Cross-check important facts across multiple sources
- Resolve conflicts by gathering additional evidence
- Only conclude when evidence is sufficient and consistent
## Output Format
In each turn, you can either call a tool or provide the final answer.
**Call a tool:**
<think>your reasoning process</think>
<tool_call>
{"name": "tool_name", "arguments": {"param1": "value1", "param2": "value2"}}
</tool_call>
**Provide final answer (when you have gathered enough information):**
<think>your reasoning and analysis</think>
<answer>the direct answer to the question</answer>
Note: All reasoning should be in <think>, <answer> should contain only the final answer.
Current date: {current_date}
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{tools_json}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
```
### Tool Definitions
The model expects tools in OpenAI function calling format:
```json
[
{
"type": "function",
"function": {
"name": "search",
"description": "Search the web via Google to find relevant information and URLs.",
"parameters": {
"type": "object",
"properties": {
"querys": {
"type": "array",
"items": {"type": "string"},
"description": "Search queries for finding relevant information."
}
},
"required": ["querys"]
}
}
},
{
"type": "function",
"function": {
"name": "visit",
"description": "Read webpage content to extract specific information, verify claims, or understand context.",
"parameters": {
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {"type": "string"},
"description": "URL(s) to visit."
},
"goal": {
"type": "string",
"description": "The specific information to retrieve. Be precise, not vague."
}
},
"required": ["urls", "goal"]
}
}
}
]
```
### Model Output Example
**Tool call turn:**
```xml
<think>
I need to search for information about X to answer the user's question.
</think>
<tool_call>
{"name": "search", "arguments": {"querys": ["search query here"]}}
</tool_call>
```
**Final answer turn:**
```xml
<think>
Based on the evidence gathered from multiple sources, I can now conclude that...
</think>
<answer>
The direct answer to the question.
</answer>
```
## Benchmark Results
Evaluated on a suite of deep search benchmarks under a maximum budget of **600 tool calls** (results from the original unquantized model).
<p align="center">
<img src="https://raw.githubusercontent.com/AIDC-AI/Marco-DeepResearch/refs/heads/main/Marco-DeepResearch-Family/Marco-Agent-DeepResearch/assets/benchmark_chart_v2.png" alt="Marco DeepResearch benchmark performance across BrowseComp, BrowseComp-ZH, xBench-DeepSearch-2510, and GAIA (text-only)" width="100%" />
</p>
## Original Model
This is a quantized version of [AIDC-AI/Marco-DeepResearch-8B](https://huggingface.co/AIDC-AI/Marco-DeepResearch-8B). Please refer to the original model card for full details on training methodology, intended use, and limitations.
- **Paper:** [Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design](https://arxiv.org/abs/2603.28376)
- **Code:** [GitHub](https://github.com/AIDC-AI/Marco-DeepResearch/tree/main/Marco-DeepResearch-Family/Marco-Agent-DeepResearch)
## Citation
```bibtex
@article{zhu2026marco,
title={Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design},
author={Bin Zhu and Qianghuai Jia and Tian Lan and Junyang Ren and Feng Gu and Feihu Jiang and Longyue Wang and Zhao Xu and Weihua Luo},
journal={arXiv preprint arXiv:2603.28376},
year={2026}
}
```
## License
This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "others", "allow_remote": true}