MiroThinker 32B SFT v0.1 needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
MiroThinker 32B SFT v0.1 – a 32.8B Qwen3 model with reasoning and tools support
MiroThinker 32B SFT v0.1 is a 32.8B parameter Qwen3 model released under Apache‑2.0. It supports reasoning and tool usage and was trained on a 40960 token context window. The model is available in multiple GGUF quantizations.
Good at
- Reasoning tasks
- Tool integration
- Long‑context handling
Limits
- No vision support
- Large VRAM requirement for higher quants
- No mixture of experts
Best for
- Complex problem solving
- API tool chaining
- Extended conversation
Who it’s for. Developers and researchers needing a large language model with reasoning and tool capabilities. The model is suitable for applications that can accommodate its memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| IQ1_S | 7.3 GB | 10.0 GB | Too big | Get file → | |
| IQ1_M | 8.0 GB | 10.6 GB | Too big | Get file → | |
| IQ2_XXS | 9.0 GB | 11.7 GB | Too big | Get file → | |
| IQ2_XS | 10.0 GB | 12.6 GB | Too big | Get file → | |
| IQ2_S | 10.5 GB | 13.2 GB | Too big | Get file → | |
| IQ2_M | 11.4 GB | 14.0 GB | Too big | Get file → | |
| Q2_K_S | 11.5 GB | 14.1 GB | Too big | Get file → | |
| Q2_K | 12.3 GB | 15.0 GB | Too big | Get file → | |
| IQ3_XXS | 12.8 GB | 15.5 GB | Too big | Get file → | |
| IQ3_XS | 13.7 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 17.0 GB | Too big | Get file → | |
| IQ3_S | 14.4 GB | 17.1 GB | Too big | Get file → | |
| IQ3_M | 14.9 GB | 17.6 GB | Too big | Get file → | |
| Q3_K_M | 16.0 GB | 18.6 GB | Too big | Get file → | |
| Q3_K_L | 17.3 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 17.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_0 | 18.7 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_S | 18.8 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_M | 19.8 GB | 22.4 GB | Too big | Get file → | |
| Q4_1 | 20.6 GB | 23.3 GB | Too big | Get file → | |
| Q5_K_S | 22.6 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 23.2 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 26.9 GB | 29.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (22.4 GB memory estimate) or Q3_K_M (18.6 GB). For 12 GB VRAM, Q5_K_M (25.9 GB) or Q6_K (29.5 GB) are options. Lower‑bit IQ quants such as IQ1_S (10 GB) or IQ1_M (10.6 GB) provide better memory efficiency.
What GPU do you need for MiroThinker 32B SFT v0.1?
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 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
Which MiroThinker 32B SFT v0.1 quant should you choose?
Q4_K_M is the usual starting point for MiroThinker 32B SFT v0.1: it balances file size and quality well. Here it is a 19.8 GB file.
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 32B SFT v0.1
How much VRAM does MiroThinker 32B SFT v0.1 need?
About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 32B SFT v0.1 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiroThinker 32B SFT v0.1 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 7.3 GB, IQ1_M is 8.0 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.5 GB and 18 more.
What context length does MiroThinker 32B SFT v0.1 support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download MiroThinker 32B SFT v0.1 GGUF?
The files are on Hugging Face in the mradermacher/MiroThinker-32B-SFT-v0.1-i1-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 32B SFT v0.1 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 this model on 8 GB VRAM?
The Q4_K_M quant uses about 22.4 GB memory at 8 k context, so 8 GB VRAM is insufficient. Lower‑bit quants like IQ1_S or IQ1_M are closer to 10 GB but still exceed 8 GB.
Does this model support vision?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.