imgmodel needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 14 quants, from 0.7 GB (Q8_0) to 6.3 GB (Q5_1). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Imgmodel: 3.47B parameter image generation model
Imgmodel is a 3.47B parameter image generation model based on the qwen3 architecture. It supports up to 40960 context tokens and is available in multiple GGUF quantizations. The model is hosted on the KoboldCpp repository.
Good at
- Image generation
- Supports large context
- Multiple quant options
Limits
- No license specified
- No vision support listed
- Large memory for high quants
Best for
- Generating high‑resolution images
- Fine‑tuning image prompts
- Batch image synthesis
Who it’s for. Developers and researchers needing a versatile image generation model with a moderate parameter count. Suitable for local deployment via llama.cpp or KoboldCpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.7 GB | 2.4 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q4_K | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q4_0 | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.0 GB | Fits | Get file → | |
| Q5_1 | 6.3 GB | 8.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q8_0 (0.68 GB, 2.4 GB memory) or Q4_0 (1.57 GB, 3.3 GB memory). For 12 GB VRAM, Q4_K_S (2.38 GB, 4.1 GB memory) or Q4_K_M (2.5 GB, 4.2 GB memory) are suitable. Higher quants require more memory.
What GPU do you need for imgmodel?
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 Q8_0 (1.8 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (3.7 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_1 (6.3 GB file, about 8.0 GB in use).
Which imgmodel quant should you choose?
Q4_K_M is the usual starting point for imgmodel: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 0.7 GB, about 0.3 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 Q8_0 at 0.7 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about imgmodel
How much VRAM does imgmodel need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 imgmodel on an 8 GB GPU?
Yes, with Q5_1: the 6.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of imgmodel GGUF?
It depends on the quant: Q8_0 is 0.7 GB, Q4_0 is 1.6 GB, Q8_0 is 1.8 GB, Q4_K_S is 2.4 GB, Q4_0 is 2.5 GB, Q4_K_M is 2.5 GB and 8 more.
What context length does imgmodel support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download imgmodel GGUF?
The files are on Hugging Face in the koboldcpp/imgmodel repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Imgmodel on 8 GB VRAM?
Yes, using Q8_0 or Q4_0 quantizations which require approximately 2.4–3.3 GB memory at 8k context.
What is the maximum context length?
Imgmodel supports up to 40960 tokens of context.
Does Imgmodel support vision tasks?
No vision support is listed for this model.