Janus Pro 7B needs about 8.7 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 5.7 GB (Q6_K).
Janus Pro 7B – 6.91B parameter Llama-based model
Janus Pro 7B is a 6.91B parameter Llama architecture model. It supports a context length of 16384 tokens and is released under the MIT license. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- Stable inference
- Versatile language tasks
Limits
- No vision support
- Requires 8k context for memory estimates
- MIT license only
Best for
- Chat applications
- Text generation
- Fine‑tuning on custom data
Who it’s for. Developers needing a large language model with a flexible context window and a permissive license. The model is suitable for research and production use where moderate VRAM is available.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 4.5 GB | Fits | Get file → | |
| IQ1_S | 1.7 GB | 6.3 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 6.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 6.6 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 6.7 GB | Fits | Get file → | |
| IQ2_S | 2.4 GB | 6.9 GB | Fits | Get file → | |
| Q2_K_S | 2.5 GB | 7.0 GB | Fits | Get file → | |
| IQ2_M | 2.5 GB | 7.1 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 7.2 GB | Tight | Get file → | |
| IQ3_XXS | 2.8 GB | 7.3 GB | Tight | Get file → | |
| IQ3_XS | 3.0 GB | 7.5 GB | Tight | Get file → | |
| IQ3_S | 3.1 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_S | 3.1 GB | 7.7 GB | Tight | Get file → | |
| IQ3_M | 3.3 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_M | 3.5 GB | 8.0 GB | Tight | Get file → | |
| Q3_K_L | 3.7 GB | 8.3 GB | Too big | Get file → | |
| IQ4_XS | 3.8 GB | 8.3 GB | Too big | Get file → | |
| IQ4_NL | 4.0 GB | 8.5 GB | Too big | Get file → | |
| Q4_0 | 4.0 GB | 8.5 GB | Too big | Get file → | |
| Q4_K_S | 4.0 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_M | 4.2 GB | 8.7 GB | Too big | Get file → | |
| Q4_1 | 4.4 GB | 8.9 GB | Too big | Get file → | |
| Q5_K_S | 4.8 GB | 9.3 GB | Too big | Get file → | |
| Q5_K_M | 4.9 GB | 9.5 GB | Too big | Get file → | |
| Q6_K | 5.7 GB | 10.2 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (1.73 GB) or IQ1_M (1.85 GB). For 12‑GB VRAM, Q2_K (2.72 GB) or Q3_K_M (3.46 GB) are suitable. For 24‑GB VRAM, Q5_K_M (4.93 GB) or Q6_K (5.67 GB) provide higher quality.
What GPU do you need for Janus Pro 7B?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_M (3.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.2 GB in use).
Which Janus Pro 7B quant should you choose?
Q4_K_M is the usual starting point for Janus Pro 7B: it balances file size and quality well. Here it is a 4.2 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 Janus Pro 7B
How much VRAM does Janus Pro 7B need?
About 8.7 GB at Q4_K_M with an 8K context window. That is the 4.2 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 7B on an 8 GB GPU?
Yes, with Q3_K_M: the 3.5 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 Janus Pro 7B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.7 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.4 GB and 19 more.
What context length does Janus Pro 7B support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.0 GB at 8K and 8.1 GB at 16K.
Where can I download Janus Pro 7B GGUF?
The files are on Hugging Face in the mradermacher/Janus-Pro-7B-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 Janus Pro 7B 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 7B on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which require about 6.3–6.4 GB of VRAM at 8k context.
Does the model support image inputs?
No, the provided GGUF files do not include vision capabilities.
What license applies to the model?
The model is released under the MIT license.