Uni MuMER Qwen3 VL 2B needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Uni MuMER Qwen3 VL 2B – vision‑language model for handwritten math recognition
Uni MuMER Qwen3 VL 2B is a 1.72B parameter model fine‑tuned for converting handwritten math images to LaTeX. It supports vision and tool usage and was trained on a 262144 token context window.
Good at
- Handwritten math to LaTeX
- Vision‑language tasks
- Tool integration
Limits
- No vision support beyond images
- Large VRAM requirement for higher quants
- Apache‑2.0 license
Best for
- Academic math transcription
- Educational content creation
- Research prototyping
Who it’s for. Developers building math transcription tools or educational software. Researchers needing a vision‑language model for handwritten expression recognition.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 0.5 GB | 2.0 GB | Fits | Get file → | |
| IQ1_M | 0.5 GB | 2.0 GB | Fits | Get file → | |
| IQ2_XXS | 0.6 GB | 2.0 GB | Fits | Get file → | |
| IQ2_XS | 0.6 GB | 2.1 GB | Fits | Get file → | |
| IQ2_S | 0.7 GB | 2.1 GB | Fits | Get file → | |
| IQ2_M | 0.7 GB | 2.1 GB | Fits | Get file → | |
| Q2_K_S | 0.7 GB | 2.2 GB | Fits | Get file → | |
| IQ3_XXS | 0.8 GB | 2.2 GB | Fits | Get file → | |
| Q2_K | 0.8 GB | 2.2 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 2.3 GB | Fits | Get file → | |
| IQ3_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| IQ3_M | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ4_NL | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_1 | 1.1 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM use IQ1_S or IQ1_M (≈2 GB memory). For 12 GB VRAM use Q2_XS or Q2_XXS (≈2.1–2 GB). For 16 GB VRAM use Q3_K_M or Q4_K_M (≈2.4–2.5 GB).
What GPU do you need for Uni MuMER Qwen3 VL 2B?
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 Q6_K (1.4 GB file, about 2.9 GB in use).
Which Uni MuMER Qwen3 VL 2B quant should you choose?
Q4_K_M is the usual starting point for Uni MuMER Qwen3 VL 2B: it balances file size and quality well. Here it is a 1.1 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 Uni MuMER Qwen3 VL 2B
How much VRAM does Uni MuMER Qwen3 VL 2B need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Uni MuMER Qwen3 VL 2B on an 8 GB GPU?
Yes, with Q6_K: the 1.4 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Uni MuMER Qwen3 VL 2B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.6 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.7 GB and 19 more.
What context length does Uni MuMER Qwen3 VL 2B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Uni MuMER Qwen3 VL 2B GGUF?
The files are on Hugging Face in the mradermacher/Uni-MuMER-Qwen3-VL-2B-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 Uni MuMER Qwen3 VL 2B 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?
Yes, use IQ1_S or IQ1_M quant, which use about 2 GB of VRAM at 8k context.
Does the model support vision tasks?
Yes, it has vision capability and can process images of handwritten math.
What license applies to this model?
The model is released under the Apache‑2.0 license.