MiroThinker-1.7-mini needs about 20.2 GB of memory at Q4_K_M (a 18.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 0.1 GB to 61.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
MiroThinker-1.7-mini: 30.5B Qwen3 MoE model with 256K context
MiroThinker-1.7-mini is a 30.5B parameter Qwen3 MoE model. It supports a 256K context window and is optimized for long‑chain reasoning and tool usage. The model is released under the apache-2.0 license.
Good at
- Long‑horizon reasoning
- Tool‑enabled task execution
- Deep multi‑step analysis
Limits
- Requires large VRAM for higher quants
- No vision support
- Only text‑only mode
Best for
- Complex research workflows
- Agentic question answering
- Multi‑step problem solving
Who it’s for. Developers building research agents or advanced LLM applications that need extended context and reasoning. The model is suitable for users with sufficient GPU memory to run higher‑quality quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XXS | 14.5 GB | 15.8 GB | Too big | Get file → | |
| IQ3_XS | 14.5 GB | 15.8 GB | Too big | Get file → | |
| Q3_K_M | 15.3 GB | 16.6 GB | Too big | Get file → | |
| Q3_K_L | 15.4 GB | 16.7 GB | Too big | Get file → | |
| IQ3_M | 15.7 GB | 17.0 GB | Too big | Get file → | |
| IQ3_S | 15.7 GB | 17.0 GB | Too big | Get file → | |
| IQ4_XS | 16.4 GB | 17.7 GB | Too big | Get file → | |
| Q4_0 | 17.2 GB | 18.5 GB | Too big | Get file → | |
| IQ4_NL | 17.3 GB | 18.6 GB | Too big | Get file → | |
| Q4_0 | 17.5 GB | 18.8 GB | Too big | Get file → | |
| Q4_K_M | 18.9 GB | 20.2 GB | Too big | Get file → | |
| Q4_K_L | 19.0 GB | 20.3 GB | Too big | Get file → | |
| Q4_1 | 19.1 GB | 20.4 GB | Too big | Get file → | |
| Q4_1 | 19.4 GB | 20.7 GB | Too big | Get file → | |
| Q5_0 | 21.0 GB | 22.3 GB | Too big | Get file → | |
| Q5_0 | 21.3 GB | 22.6 GB | Too big | Get file → | |
| Q5_K_M | 22.3 GB | 23.6 GB | Too big | Get file → | |
| Q5_K_L | 22.5 GB | 23.8 GB | Too big | Get file → | |
| Q5_1 | 22.9 GB | 24.3 GB | Too big | Get file → | |
| Q5_1 | 23.1 GB | 24.4 GB | Too big | Get file → | |
| Q6_K_M | 25.1 GB | 26.4 GB | Too big | Get file → | |
| Q6_K_L | 25.2 GB | 26.5 GB | Too big | Get file → | |
| Q8_0 | 32.5 GB | 33.8 GB | Too big | Get file → | |
| BF16 | 55.3 GB (2 parts) | 56.7 GB | Too big | Get file → | |
| F16 | 55.3 GB (2 parts) | 56.7 GB | Too big | Get file → | |
| F16 | 61.1 GB (2 parts) | 62.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_XXS or IQ3_XS (file size 14.46 GB, memory 15.8 GB). For 16 GB VRAM, Q4_K_M or Q4_K_L (file size 18.88–19.03 GB, memory 20.2–20.3 GB). For 24 GB VRAM, Q5_K_M or Q5_K_L (file size 22.31–22.46 GB, memory 23.6–23.8 GB).
What GPU do you need for MiroThinker-1.7-mini?
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 the main file (0.1 GB file, about 1.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XS (14.5 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_L (22.5 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_L (25.2 GB file, about 26.5 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 MiroThinker-1.7-mini quant should you choose?
Q4_K_M is the usual starting point for MiroThinker-1.7-mini: it balances file size and quality well. Here it is a 18.9 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 MiroThinker-1.7-mini
How much VRAM does MiroThinker-1.7-mini need?
About 20.2 GB at Q4_K_M with an 8K context window. That is the 18.9 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 MiroThinker-1.7-mini 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 MiroThinker-1.7-mini GGUF?
It depends on the quant: file is 0.1 GB, IQ3_XXS is 14.5 GB, IQ3_XS is 14.5 GB, Q3_K_M is 15.3 GB, Q3_K_L is 15.4 GB, IQ3_M is 15.7 GB and 21 more.
What context length does MiroThinker-1.7-mini support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 MiroThinker-1.7-mini GGUF?
The files are on Hugging Face in the Mungert/MiroThinker-1.7-mini-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 MiroThinker-1.7-mini 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 MiroThinker-1.7-mini on 8 GB VRAM?
Yes, using IQ3_XXS or IQ3_XS quantizations, which estimate 15.8 GB memory at 8 k context.
Does the model support vision inputs?
No, the model is text‑only and does not support vision.
What is the maximum context length?
The model supports a native context length of 262,144 tokens.