65 lines
1.4 KiB
Markdown
65 lines
1.4 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model: miromind-ai/MiroThinker-1.7-mini
|
|
tags:
|
|
- gguf
|
|
- quantized
|
|
- qwen3_moe
|
|
- text-generation
|
|
- agent
|
|
- deep-research
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# MiroThinker-1.7-mini GGUF Q8_0
|
|
|
|
Q8_0 GGUF quantization of [miromind-ai/MiroThinker-1.7-mini](https://huggingface.co/miromind-ai/MiroThinker-1.7-mini).
|
|
|
|
## Model Details
|
|
|
|
- **Original Model:** miromind-ai/MiroThinker-1.7-mini (Qwen3 MoE, 30.5B params)
|
|
- **Quantization:** Q8_0 (8-bit)
|
|
- **File Size:** ~31 GB
|
|
- **Format:** GGUF (llama.cpp compatible)
|
|
- **Max Context:** 256K tokens
|
|
- **Max Tool Calls:** 300
|
|
|
|
## About MiroThinker-1.7-mini
|
|
|
|
MiroThinker-1.7-mini is a deep research agent model fine-tuned from Qwen3-30B-A3B-Thinking-2507. It achieves state-of-the-art performance in deep research tasks among open-source models.
|
|
|
|
### Benchmarks (original BF16)
|
|
|
|
| Benchmark | Score |
|
|
|-----------|-------|
|
|
| BrowseComp | 74.0% |
|
|
| BrowseComp-ZH | 75.3% (SOTA) |
|
|
| GAIA-Val-165 | 82.7% |
|
|
| HLE-Text | 42.9% |
|
|
|
|
## Usage
|
|
|
|
Works with any GGUF-compatible runtime: llama.cpp, Ollama, LM Studio, etc.
|
|
|
|
**Ollama:**
|
|
```bash
|
|
ollama run hf.co/DJLougen/MiroThinker-1.7-mini-GGUF-Q8_0
|
|
```
|
|
|
|
**llama.cpp:**
|
|
```bash
|
|
llama-cli -m MiroThinker-1.7-mini-Q8_0.gguf -c 8192 -n 512
|
|
```
|
|
|
|
## Recommended Parameters
|
|
|
|
- temperature: 1.0
|
|
- top_p: 0.95
|
|
- repetition_penalty: 1.05
|
|
|
|
## Credits
|
|
|
|
- Original model by [miromind-ai](https://huggingface.co/miromind-ai)
|
|
- Quantized by [DJLougen](https://huggingface.co/DJLougen) using llama.cpp
|