imajev 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 11 quants, from 1.0 GB (Q3_K_S) to 2.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
imajev 2b – a 1.88B parameter vision‑language model
imajev 2b is a 1.88B parameter model based on Qwen3.5. It supports vision tasks and has a trained context of 262144 tokens. The model is released under the Apache‑2.0 license and is suitable for prototyping and research.
Good at
- Vision‑language inference
- Multimodal reasoning
- Fine‑tuning for research
Limits
- No explicit language list provided
- Requires a vision encoder
- Large VRAM for higher context
Best for
- Image captioning
- Visual question answering
- Multimodal fine‑tuning
Who it’s for. Developers and researchers needing a small vision‑language model for prototyping or fine‑tuning. The model is open‑source under Apache‑2.0 and can be run locally with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 1.0 GB | 1.9 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 → | |
| Q4_0 | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_0 | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_1 | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.27 GB file, ~2.2 GB RAM). If 12 GB VRAM is available, Q5_K_M (1.41 GB file, ~2.3 GB RAM) offers higher quality. Larger VRAM allows Q8_0 (2.01 GB file, ~2.9 GB RAM).
What GPU do you need for imajev 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 Q8_0 (2.0 GB file, about 2.9 GB in use).
Which imajev 2b quant should you choose?
Q4_K_M is the usual starting point for imajev 2b: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.0 GB, about 1.6 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 Q3_K_S at 1.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about imajev 2b
How much VRAM does imajev 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 imajev 2b on an 8 GB GPU?
Yes, with Q8_0: the 2.0 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 imajev 2b GGUF?
It depends on the quant: Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.2 GB, Q4_0 is 1.2 GB, Q4_K_S is 1.2 GB, Q4_K_M is 1.3 GB and 5 more.
What context length does imajev 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 imajev 2b GGUF?
The files are on Hugging Face in the mindchain/imajev-2b-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 imajev 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 imajev 2b on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 2.2 GB of RAM at 8 k context.
Does imajev 2b support multiple languages?
The model is trained on 201 languages, but no specific language list is provided in the card.
Is imajev 2b free to use?
Yes, it is released under the Apache‑2.0 license and can be used for research and prototyping.