Janus Pro 1B needs about 3.1 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.7 GB (Q2_K) to 3.3 GB (F16).
Janus Pro 1B – a 1.65B parameter multimodal LLM
Janus Pro 1B is a 1.65B parameter model built on the DeepSeek family. It supports vision and text generation with a 16384 token context window. The model is released under the MIT license.
Good at
- Vision‑text multimodal tasks
- Image generation from prompts
- Unified understanding and generation
Limits
- No explicit vision limits beyond 384x384 input
- Requires 8‑k context for memory estimates
- No mention of audio or other modalities
Best for
- Developers building multimodal chatbots
- Researchers testing vision‑language models
- Prototyping image generation pipelines
Who it’s for. The model is suitable for developers and researchers who need a lightweight multimodal LLM that can run on consumer hardware. It is ideal for projects that require both visual understanding and text‑to‑image generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.7 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_L | 0.9 GB | 3.0 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_S | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_M | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.9 GB | Fits | Get file → | |
| F16 | 3.3 GB | 5.4 GB | Fits | Get file → |
For 8‑GB VRAM use Q4_K_M (1.04 GB file, ~3.1 GB memory). For 4‑GB VRAM use Q3_K_M (0.86 GB file, ~3 GB memory). For 2‑GB VRAM use Q2_K (0.7 GB file, ~2.8 GB memory). Estimates are approximate.
What GPU do you need for Janus Pro 1B?
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 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.3 GB file, about 5.4 GB in use).
Which Janus Pro 1B quant should you choose?
Q4_K_M is the usual starting point for Janus Pro 1B: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.8 GB, about 1.7 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 Q2_K at 0.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Janus Pro 1B
How much VRAM does Janus Pro 1B need?
About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Janus Pro 1B on an 8 GB GPU?
Yes, with F16: the 3.3 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Janus Pro 1B GGUF?
It depends on the quant: Q2_K is 0.7 GB, Q3_K_S is 0.8 GB, Q3_K_M is 0.9 GB, Q3_K_L is 0.9 GB, IQ4_XS is 0.9 GB, Q4_K_S is 1.0 GB and 6 more.
What context length does Janus Pro 1B support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.
Where can I download Janus Pro 1B GGUF?
The files are on Hugging Face in the mradermacher/Janus-Pro-1B-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 Janus Pro 1B use?
Hugging Face lists the license as mit. 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 Janus Pro 1B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 3.1 GB memory at 8‑k context, fitting within 8 GB VRAM.
Does the model support image generation?
Yes, Janus Pro can generate images from prompts using its image generation mode.
What license applies to the model?
The model is released under the MIT license and is subject to the DeepSeek Model License.