Uni MuMER Qwen3.5 2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 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 1.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Uni MuMER Qwen3.5 2B – Vision‑language model for handwritten math recognition
Uni MuMER Qwen3.5 2B is a fine‑tuned vision‑language model based on Qwen3.5‑2B. It converts images of handwritten mathematical expressions into LaTeX. The model supports reasoning, tools, and vision tasks.
Good at
- Handwritten math to LaTeX conversion
- Vision‑language reasoning
- Tool‑assisted inference
Limits
- No vision support in non‑vision quant files
- Large VRAM requirement for high context
- Apache‑2.0 license restricts commercial use without compliance
Best for
- Academic research on HMER
- Educational content generation
- Prototype vision‑language applications
Who it’s for. Researchers and developers needing a lightweight vision‑language model for handwritten mathematical expression recognition. The model is suitable for environments with moderate GPU memory and compliance with the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ1_S | 0.7 GB | 1.6 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XS | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_S | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_M | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ3_XXS | 0.9 GB | 1.8 GB | Fits | Get file → | |
| Q2_K_S | 0.9 GB | 1.8 GB | Fits | Get file → | |
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ3_XS | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ3_S | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ3_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_0 | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_NL | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q4_1 | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (0.72 GB, 1.6 GB memory at 8k context) or Q2_XXS (0.79 GB, 1.7 GB). For 12 GB VRAM, Q4_K_M (1.27 GB, 2.2 GB) offers a balance of size and performance. Larger models like Q6_K (1.56 GB, 2.5 GB) require 16 GB or more.
What GPU do you need for Uni MuMER Qwen3.5 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 (1.6 GB file, about 2.5 GB in use).
Which Uni MuMER Qwen3.5 2B quant should you choose?
Q4_K_M is the usual starting point for Uni MuMER Qwen3.5 2B: it balances file size and quality well. Here it is a 1.3 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 Qwen3.5 2B
How much VRAM does Uni MuMER Qwen3.5 2B need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Qwen3.5 2B on an 8 GB GPU?
Yes, with Q6_K: the 1.6 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Uni MuMER Qwen3.5 2B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.8 GB, IQ2_S is 0.8 GB and 19 more.
What context length does Uni MuMER Qwen3.5 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 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Uni MuMER Qwen3.5 2B GGUF?
The files are on Hugging Face in the mradermacher/Uni-MuMER-Qwen3.5-2B-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 Qwen3.5 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 Q2_XXS quant files; they estimate 1.6–1.7 GB memory at 8k context.
Does the model support vision tasks?
Yes, the base model includes vision support; ensure you use a quant file that retains vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license, which allows modification and redistribution with attribution.