bagel needs about 10.4 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 0.2 GB (F16) to 15.9 GB (Q8_0).
14.6B parameter multimodal model for text and image tasks
Bagel is a 14.6B parameter multimodal foundation model based on the pig architecture. It supports text and image understanding, generation, and editing. The model is released under the apache-2.0 license.
Good at
- Multimodal understanding
- Text‑to‑image generation
- Free‑form image editing
Limits
- No vision support in the base GGUF file
- Requires large VRAM for higher precision quants
- No explicit context length limit provided
Best for
- Developers building multimodal applications
- Researchers testing image‑editing capabilities
- Users needing a unified text‑image model
Who it’s for. Bagel is suitable for developers and researchers who need a single model for both text and image tasks. It is ideal for those who want to experiment with multimodal generation and editing without training a new model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F32 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q2_K | 5.5 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_M | 7.0 GB | 8.3 GB | Too big | Get file → | |
| Q4_0 | 8.9 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 8.9 GB | 10.4 GB | Too big | Get file → | |
| Q4_1 | 9.7 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_M | 10.6 GB | 12.4 GB | Too big | Get file → | |
| Q5_0 | 10.6 GB | 12.4 GB | Too big | Get file → | |
| Q5_1 | 11.5 GB | 13.4 GB | Too big | Get file → | |
| Q6_K | 12.5 GB | 14.5 GB | Too big | Get file → | |
| Q8_0 | 15.9 GB | 18.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 8.85 GB, estimated memory 10.4 GB). For 12 GB VRAM, Q5_0 (10.62 GB, 12.4 GB). For 16 GB VRAM, Q6_K (12.5 GB, 14.5 GB). Higher precision quants increase memory usage.
What GPU do you need for bagel?
These figures add the file size, an fp16 KV cache at an 8K context window 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 F32 (0.3 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (0.3 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K (5.5 GB file, about 6.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (9.7 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.5 GB file, about 14.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.9 GB file, about 18.3 GB in use).
Which bagel quant should you choose?
Q4_K_M is the usual starting point for bagel: it balances file size and quality well. Here it is a 8.9 GB file.
The Q8_0 file is 15.9 GB, about 1.8 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 F16 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about bagel
How much VRAM does bagel need?
About 10.4 GB at Q4_K_M with an 8K context window. That is the 8.9 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 bagel on an 8 GB GPU?
Yes, with Q2_K: the 5.5 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bagel GGUF?
It depends on the quant: F16 is 0.2 GB, F32 is 0.3 GB, Q2_K is 5.5 GB, Q3_K_M is 7.0 GB, Q4_0 is 8.9 GB, Q4_K_M is 8.9 GB and 6 more.
Where can I download bagel GGUF?
The files are on Hugging Face in the calcuis/bagel-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 bagel 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 Bagel on 8 GB VRAM?
Use the Q4_0 quant, which requires about 10.4 GB of VRAM at 8k context. It may fit with memory optimizations.
Does Bagel support vision tasks?
Yes, Bagel is a multimodal model with image understanding and generation capabilities.