Januscoder-8B needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 26 quants, from 2.3 GB (IQ1_S) to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
JanusCoder‑8B – multimodal code generation model
JanusCoder‑8B is an 8.19B‑parameter model built on the InternLM family with Qwen3 architecture. It supports coding and vision tasks and is trained on the JANUSCODE‑800K multimodal code corpus. The model is released under the apache‑2.0 license.
Good at
- Code generation from text or images
- Visual‑programmatic editing
- Interactive front‑end creation
Limits
- No vision support in llama.cpp without --jinja
- Large context requires high VRAM
- Requires at least 8.4 GB VRAM for Q6_K
Best for
- Generating code snippets from screenshots
- Creating data visualizations programmatically
- Editing complex animation code
Who it’s for. Developers and researchers needing a unified visual‑programmatic interface for code intelligence. The model is suitable for projects that combine textual and visual inputs to produce or modify code.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ1_M | 2.4 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XXS | 2.6 GB | 4.3 GB | Fits | Get file → | |
| IQ2_M | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.4 GB | 5.1 GB | Fits | Get file → | |
| Q2_K_L | 3.4 GB | 5.1 GB | Fits | Get file → | |
| Q2_K_XL | 3.5 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_XL | 4.3 GB | 6.0 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 4.8 GB | 6.5 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q4_K_XL | 5.1 GB | 6.8 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_XL | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q6_K_XL | 7.5 GB | 9.2 GB | Too big | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → | |
| Q8_K_XL | 10.8 GB | 12.5 GB | Too big | Get file → | |
| BF16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q6_K (6.73 GB file, 8.4 GB memory at 8k context). With 12 GB VRAM, Q8_K_XL (10.82 GB file, 12.5 GB memory) offers higher precision. For limited memory, IQ1_S (2.28 GB file, 4 GB memory) is a lightweight option.
What GPU do you need for Januscoder-8B?
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 IQ1_S (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_XL (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_XL (5.9 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_K_XL (10.8 GB file, about 12.5 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).
Which Januscoder-8B quant should you choose?
Q4_K_M is the usual starting point for Januscoder-8B: it balances file size and quality well. Here it is a 5.0 GB file.
The Q8_0 file is 8.7 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 IQ1_S at 2.3 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 Januscoder-8B
How much VRAM does Januscoder-8B need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Januscoder-8B on an 8 GB GPU?
Yes, with Q5_K_XL: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Januscoder-8B GGUF?
It depends on the quant: IQ1_S is 2.3 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.6 GB, IQ2_M is 3.1 GB, Q2_K is 3.3 GB, IQ3_XXS is 3.4 GB and 20 more.
What context length does Januscoder-8B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Januscoder-8B GGUF?
The files are on Hugging Face in the unsloth/JanusCoder-8B-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 Januscoder-8B 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 JanusCoder‑8B on 8 GB VRAM?
Yes, the Q6_K quant requires about 8.4 GB VRAM at 8k context. Use a lower quant if you need less memory.
Does the model support vision in llama.cpp?
Vision support requires the --jinja flag in llama.cpp. Without it, only text generation is available.
What license applies to this model?
The model is released under the apache‑2.0 license.