MiroThinker v1.0 72B needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.0 GB to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
MiroThinker v1.0 72B – 256K context, 600 tool calls, 72.7B parameters
MiroThinker v1.0 72B is an open‑source research agent built on the qwen2 architecture. It supports a 256K context window and up to 600 tool calls per task. The model is trained for deep, multi‑step reasoning and interactive scaling.
Good at
- Long‑horizon reasoning
- Tool‑augmented tasks
- Large context handling
Limits
- No vision support
- Requires large VRAM for full precision
- MIT license only
Best for
- Research agents needing deep interaction
- Tool‑centric workflows
- Large‑context simulations
Who it’s for. Researchers and developers building agent‑based systems that require extensive reasoning and tool use. The model is suitable for environments where a 256K context window and high tool‑call capacity are needed.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_M | 23.7 GB | 26.9 GB | Too big | Get file → | |
| IQ2_XXS | 25.5 GB | 28.7 GB | Too big | Get file → | |
| IQ2_XS | 27.1 GB | 30.2 GB | Too big | Get file → | |
| IQ2_S | 27.9 GB | 31.1 GB | Too big | Get file → | |
| IQ2_M | 29.3 GB | 32.5 GB | Too big | Get file → | |
| Q2_K | 29.8 GB | 33.0 GB | Too big | Get file → | |
| Q2_K_L | 31.0 GB | 34.2 GB | Too big | Get file → | |
| IQ3_XXS | 31.8 GB | 35.0 GB | Too big | Get file → | |
| IQ3_XS | 32.8 GB | 36.0 GB | Too big | Get file → | |
| Q3_K_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| IQ3_M | 35.5 GB | 38.7 GB | Too big | Get file → | |
| Q3_K_M | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q3_K_L | 39.5 GB | 42.7 GB | Too big | Get file → | |
| IQ4_XS | 39.7 GB | 42.9 GB | Too big | Get file → | |
| Q3_K_XL | 40.6 GB | 43.8 GB | Too big | Get file → | |
| IQ4_NL | 41.3 GB | 44.5 GB | Too big | Get file → | |
| Q4_0 | 41.4 GB | 44.6 GB | Too big | Get file → | |
| Q4_K_S | 43.9 GB | 47.1 GB | Too big | Get file → | |
| Q4_1 | 45.7 GB | 48.9 GB | Too big | Get file → | |
| Q4_K_M | 47.4 GB | 50.6 GB | Too big | Get file → | |
| Q4_K_L | 48.3 GB | 51.5 GB | Too big | Get file → | |
| Q5_K_S | 51.4 GB (2 parts) | 54.6 GB | Too big | Get file → | |
| Q5_K_M | 54.4 GB (2 parts) | 57.6 GB | Too big | Get file → | |
| Q6_K | 64.3 GB (2 parts) | 67.5 GB | Too big | Get file → | |
| Q8_0 | 77.3 GB (2 parts) | 80.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (23.74 GB file, 26.9 GB memory at 8K context). For 12 GB VRAM, Q4_K_M (47.42 GB file, 50.6 GB memory) is a good balance. For 24 GB VRAM, Q6_K (64.35 GB file, 67.5 GB memory) or Q8_0 (77.26 GB file, 80.4 GB memory) can be considered. Estimates are approximate.
What GPU do you need for MiroThinker v1.0 72B?
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 (0.0 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 32 GB VRAM: the best quant that fits is IQ2_S (27.9 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).
Which MiroThinker v1.0 72B quant should you choose?
Q4_K_M is the usual starting point for MiroThinker v1.0 72B: it balances file size and quality well. Here it is a 47.4 GB file.
The Q8_0 file is 77.3 GB, about 1.6 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 0.0 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 72B
How much VRAM does MiroThinker v1.0 72B need?
About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 72B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiroThinker v1.0 72B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_M is 23.7 GB, IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_S is 27.9 GB, IQ2_M is 29.3 GB and 20 more.
What context length does MiroThinker v1.0 72B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download MiroThinker v1.0 72B GGUF?
The files are on Hugging Face in the bartowski/miromind-ai_MiroThinker-v1.0-72B-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 72B 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 72B on 8 GB VRAM?
Only the IQ1_M quant can be run on 8 GB VRAM, as it requires 26.9 GB memory at 8K context, which is the closest fit to the VRAM limit.
Does the model support vision tasks?
No, the model does not support vision capabilities.
What license does the model use?
The model is released under the MIT license.