MiroThinker-v1.5-30B 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 40 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‑v1.5‑30B: 30.5B‑parameter MoE model with 256K context for advanced reasoning
MiroThinker‑v1.5‑30B is a 30.5B‑parameter Mixture of Experts model based on Qwen3‑30B‑A3B‑Thinking‑2507. It supports a native context length of 262,144 tokens and is optimized for long‑horizon reasoning and tool‑augmented tasks.
Good at
- Long‑horizon reasoning
- Tool‑augmented interactions
- 256K context handling
Limits
- Requires high VRAM for full precision
- No vision support
- Large context length demands significant memory
Best for
- Complex reasoning workflows
- Agent‑driven tool usage
- Large‑context document analysis
Who it’s for. Developers building advanced reasoning agents or researchers needing deep context understanding. Suitable for environments where 256K context and MoE capabilities are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 9.6 GB | 10.9 GB | Too big | Get file → | |
| IQ2_XXS | 10.4 GB | 11.7 GB | Too big | Get file → | |
| IQ1_M | 11.0 GB | 12.3 GB | Too big | Get file → | |
| IQ2_S | 12.4 GB | 13.7 GB | Too big | Get file → | |
| IQ2_XS | 12.7 GB | 14.0 GB | Too big | Get file → | |
| IQ2_M | 12.9 GB | 14.2 GB | Too big | Get file → | |
| IQ3_XXS | 14.4 GB | 15.7 GB | Too big | Get file → | |
| IQ3_XS | 14.5 GB | 15.8 GB | Too big | Get file → | |
| Q2_K_S | 15.6 GB | 16.9 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 → | |
| Q2_K_M | 15.7 GB | 17.0 GB | Too big | Get file → | |
| Q2_K_L | 15.8 GB | 17.1 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_S | 18.2 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_S | 18.8 GB | 20.1 GB | Too big | Get file → | |
| Q3_K_M | 18.9 GB | 20.2 GB | Too big | Get file → | |
| Q4_K_M | 18.9 GB | 20.2 GB | Too big | Get file → | |
| Q3_K_L | 19.0 GB | 20.3 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_S | 21.9 GB | 23.2 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 → | |
| BF16 | 61.1 GB (2 parts) | 62.4 GB | Too big | Get file → | |
| F16 | 61.1 GB (2 parts) | 62.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 9.56 GB, memory 10.9 GB at 8 k context). For 12 GB VRAM, IQ2_S (12.37 GB, 13.7 GB). For 16 GB VRAM, Q4_K_S (18.18 GB, 19.5 GB). Larger budgets can use higher‑precision quants such as Q5_K_M or Q6_K_M.
What GPU do you need for MiroThinker-v1.5-30B?
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 IQ2_XXS (10.4 GB file, about 11.7 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-v1.5-30B quant should you choose?
Q4_K_M is the usual starting point for MiroThinker-v1.5-30B: 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-v1.5-30B
How much VRAM does MiroThinker-v1.5-30B 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-v1.5-30B 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-v1.5-30B GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 9.6 GB, IQ2_XXS is 10.4 GB, IQ1_M is 11.0 GB, IQ2_S is 12.4 GB, IQ2_XS is 12.7 GB and 34 more.
What context length does MiroThinker-v1.5-30B 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-v1.5-30B GGUF?
The files are on Hugging Face in the Mungert/MiroThinker-v1.5-30B-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-v1.5-30B 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‑v1.5‑30B on 8 GB VRAM?
The IQ1_S quant requires about 10.9 GB at 8 k context, so 8 GB VRAM is insufficient for full inference.
Does this model support vision tasks?
No, the model has no vision capability.
What is the maximum context length?
The native context length is 262,144 tokens, enabling 256K context usage.