MiroThinker v1.5 235B needs about 144.2 GB of memory at Q4_K_M (a 142.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.5 GB to 193.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.
MiroThinker v1.5 235B is a 235B-parameter Mirothinker model in GGUF format, quantized by mradermacher. Its trained context length is 256K tokens. The repository has 24 quant files, from 0.5 GB to 193.0 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 2.6 GB | Fits | Get file → | |
| IQ1_S | 47.9 GB | 50.0 GB | Too big | Get file → | |
| IQ1_M | 53.1 GB | 55.2 GB | Too big | Get file → | |
| IQ2_XXS | 61.8 GB | 63.9 GB | Too big | Get file → | |
| IQ2_XS | 68.8 GB | 70.9 GB | Too big | Get file → | |
| IQ2_S | 70.2 GB | 72.3 GB | Too big | Get file → | |
| IQ2_M | 77.2 GB | 79.2 GB | Too big | Get file → | |
| Q2_K_S | 79.8 GB | 81.8 GB | Too big | Get file → | |
| Q2_K | 85.7 GB | 87.8 GB | Too big | Get file → | |
| IQ3_XXS | 90.4 GB | 92.5 GB | Too big | Get file → | |
| IQ3_XS | 96.0 GB | 98.0 GB | Too big | Get file → | |
| Q3_K_S | 101.4 GB | 103.5 GB | Too big | Get file → | |
| IQ3_S | 101.5 GB | 103.5 GB | Too big | Get file → | |
| IQ3_M | 103.1 GB | 105.1 GB | Too big | Get file → | |
| Q3_K_M | 112.4 GB | 114.5 GB | Too big | Get file → | |
| Q3_K_L | 121.8 GB | 123.9 GB | Too big | Get file → | |
| IQ4_XS | 125.3 GB | 127.4 GB | Too big | Get file → | |
| Q4_0 | 133.1 GB | 135.2 GB | Too big | Get file → | |
| Q4_K_S | 133.7 GB | 135.8 GB | Too big | Get file → | |
| Q4_K_M | 142.2 GB | 144.2 GB | Too big | Get file → | |
| Q4_1 | 147.2 GB | 149.3 GB | Too big | Get file → | |
| Q5_K_S | 161.9 GB | 164.0 GB | Too big | Get file → | |
| Q5_K_M | 166.8 GB | 168.9 GB | Too big | Get file → | |
| Q6_K | 193.0 GB | 195.1 GB | Too big | Get file → |
What GPU do you need for MiroThinker v1.5 235B?
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 (0.5 GB file, about 2.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
Which MiroThinker v1.5 235B quant should you choose?
Q4_K_M is the usual starting point for MiroThinker v1.5 235B: it balances file size and quality well. Here it is a 142.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.5 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 235B
How much VRAM does MiroThinker v1.5 235B need?
About 144.2 GB at Q4_K_M with an 8K context window. That is the 142.2 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 235B on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiroThinker v1.5 235B GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 47.9 GB, IQ1_M is 53.1 GB, IQ2_XXS is 61.8 GB, IQ2_XS is 68.8 GB, IQ2_S is 70.2 GB and 18 more.
What context length does MiroThinker v1.5 235B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.
Where can I download MiroThinker v1.5 235B GGUF?
The files are on Hugging Face in the mradermacher/MiroThinker-v1.5-235B-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 v1.5 235B 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.