MiroThinker-v1.0-30B needs about 20.3 GB of memory at Q4_K_M (a 19.0 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 (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
MiroThinker‑v1.0‑30B: 30.5B‑parameter MoE model with 256K context
MiroThinker‑v1.0‑30B is a 30.5B‑parameter Qwen3 MoE model. It supports 262,144‑token context and is optimized for reasoning and tool usage. The model is released under the MIT license.
Good at
- Reasoning
- Tool usage
- Long‑context understanding
Limits
- No vision support
- Requires enable_thinking mode
- Large VRAM needed for full precision
Best for
- Complex reasoning tasks
- Tool‑integrated workflows
- Academic problem solving
Who it’s for. Developers and researchers needing a large‑scale MoE language model for advanced reasoning. The model is suitable for applications that can handle its high memory demands and benefit from its 256K context capability.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 9.1 GB | 10.4 GB | Too big | Get file → | |
| IQ2_XXS | 9.8 GB | 11.1 GB | Too big | Get file → | |
| IQ1_M | 10.0 GB | 11.3 GB | Too big | Get file → | |
| IQ2_XS | 11.0 GB | 12.3 GB | Too big | Get file → | |
| IQ2_S | 11.0 GB | 12.3 GB | Too big | Get file → | |
| IQ2_M | 11.5 GB | 12.8 GB | Too big | Get file → | |
| Q2_K_S | 11.9 GB | 13.2 GB | Too big | Get file → | |
| Q2_K_M | 12.0 GB | 13.3 GB | Too big | Get file → | |
| IQ3_XXS | 13.7 GB | 15.0 GB | Too big | Get file → | |
| IQ3_XS | 13.8 GB | 15.1 GB | Too big | Get file → | |
| IQ3_M | 15.4 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_S | 15.8 GB | 17.1 GB | Too big | Get file → | |
| Q3_K_M | 15.8 GB | 17.2 GB | Too big | Get file → | |
| IQ4_XS | 16.5 GB | 17.8 GB | Too big | Get file → | |
| IQ4_NL | 17.2 GB | 18.5 GB | Too big | Get file → | |
| Q4_0 | 17.5 GB | 18.8 GB | Too big | Get file → | |
| Q4_K_S | 18.2 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_M | 19.0 GB | 20.3 GB | Too big | Get file → | |
| Q4_1 | 19.2 GB | 20.5 GB | Too big | Get file → | |
| Q5_0 | 21.3 GB | 22.6 GB | Too big | Get file → | |
| Q5_K_M | 22.5 GB | 23.8 GB | Too big | Get file → | |
| Q5_1 | 23.1 GB | 24.4 GB | Too big | Get file → | |
| Q6_K_M | 25.2 GB | 26.5 GB | Too big | Get file → | |
| Q8_0 | 32.5 GB | 33.8 GB | Too big | Get file → | |
| F16 | 38.7 GB | 40.0 GB | Too big | Get file → | |
| BF16 | 61.1 GB (2 parts) | 62.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (19.03 GB file, 20.3 GB memory at 8k context). For 16 GB VRAM, Q5_K_M (22.46 GB file, 23.8 GB memory) is recommended. For 32 GB VRAM, Q8_0 (32.48 GB file, 33.8 GB memory) provides full precision.
What GPU do you need for MiroThinker-v1.0-30B?
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 IQ1_M (10.0 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XS (13.8 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (22.5 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_M (25.2 GB file, about 26.5 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (38.7 GB file, about 40.0 GB in use).
Which MiroThinker-v1.0-30B quant should you choose?
Q4_K_M is the usual starting point for MiroThinker-v1.0-30B: it balances file size and quality well. Here it is a 19.0 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-v1.0-30B
How much VRAM does MiroThinker-v1.0-30B need?
About 20.3 GB at Q4_K_M with an 8K context window. That is the 19.0 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 MiroThinker-v1.0-30B 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-v1.0-30B GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 9.1 GB, IQ2_XXS is 9.8 GB, IQ1_M is 10.0 GB, IQ2_XS is 11.0 GB, IQ2_S is 11.0 GB and 21 more.
What context length does MiroThinker-v1.0-30B 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-v1.0-30B GGUF?
The files are on Hugging Face in the Mungert/MiroThinker-v1.0-30B-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-v1.0-30B use?
Hugging Face lists the license as mit. 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‑v1.0‑30B on 8 GB VRAM?
Only the Q4_K_M quantization fits within 8 GB VRAM, but memory usage is approximate and may exceed limits on some setups.
Does the model support vision tasks?
No, the model does not support vision capabilities.
What license applies to this model?
The model is released under the MIT license.