Januscoder-14B needs about 10.8 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 26 quants, from 3.8 GB (IQ1_S) to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
JanusCoder‑14B – a multimodal code intelligence model
JanusCoder‑14B is a 14.8B‑parameter model built on the InternLM family with Qwen3 architecture. It supports coding, reasoning, tools, and vision tasks. The model is trained on JANUSCODE‑800K, a large multimodal code corpus.
Good at
- Code generation from text and images
- Program‑driven editing of visual effects
- Complex animation construction
Limits
- No vision support in llama.cpp without --jinja
- Requires 8k context for full capability
- License is apache‑2.0
Best for
- Developers needing code from visual prompts
- Researchers exploring multimodal code models
- Teams building interactive front‑ends
Who it’s for. Developers and researchers who need a unified visual‑programmatic interface for code generation and editing. The model is open‑source under apache‑2.0 and can be integrated into existing pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.8 GB | 5.7 GB | Fits | Get file → | |
| IQ1_M | 4.1 GB | 5.9 GB | Fits | Get file → | |
| IQ2_XXS | 4.5 GB | 6.3 GB | Fits | Get file → | |
| IQ2_M | 5.4 GB | 7.3 GB | Tight | Get file → | |
| Q2_K | 5.8 GB | 7.6 GB | Tight | Get file → | |
| Q2_K_L | 5.9 GB | 7.8 GB | Tight | Get file → | |
| IQ3_XXS | 6.0 GB | 7.9 GB | Tight | Get file → | |
| Q2_K_XL | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_S | 6.7 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_M | 7.3 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_XL | 7.6 GB | 9.4 GB | Too big | Get file → | |
| IQ4_XS | 8.1 GB | 10.0 GB | Too big | Get file → | |
| IQ4_NL | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q4_0 | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_S | 8.6 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 9.0 GB | 10.8 GB | Too big | Get file → | |
| Q4_K_XL | 9.1 GB | 11.0 GB | Too big | Get file → | |
| Q4_1 | 9.4 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_S | 10.3 GB | 12.1 GB | Too big | Get file → | |
| Q5_K_M | 10.5 GB | 12.4 GB | Too big | Get file → | |
| Q5_K_XL | 10.5 GB | 12.4 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 14.0 GB | Too big | Get file → | |
| Q6_K_XL | 13.3 GB | 15.1 GB | Too big | Get file → | |
| Q8_0 | 15.7 GB | 17.5 GB | Too big | Get file → | |
| Q8_K_XL | 18.8 GB | 20.6 GB | Too big | Get file → | |
| BF16 | 29.5 GB | 31.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3.83 GB) or IQ1_M (4.06 GB). For 12 GB VRAM, IQ4_K_M (9 GB) or Q4_K_XL (9.14 GB) are suitable. For 20 GB VRAM, Q8_K_XL (18.75 GB) provides the highest fidelity.
What GPU do you need for Januscoder-14B?
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 IQ1_M (4.1 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_XL (6.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (9.4 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_XL (13.3 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_K_XL (18.8 GB file, about 20.6 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.4 GB in use).
Which Januscoder-14B quant should you choose?
Q4_K_M is the usual starting point for Januscoder-14B: it balances file size and quality well. Here it is a 9.0 GB file.
The Q8_0 file is 15.7 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 3.8 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-14B
How much VRAM does Januscoder-14B need?
About 10.8 GB at Q4_K_M with an 8K context window. That is the 9.0 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-14B on an 8 GB GPU?
Yes, with Q2_K_XL: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Januscoder-14B GGUF?
It depends on the quant: IQ1_S is 3.8 GB, IQ1_M is 4.1 GB, IQ2_XXS is 4.5 GB, IQ2_M is 5.4 GB, Q2_K is 5.8 GB, Q2_K_L is 5.9 GB and 20 more.
What context length does Januscoder-14B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Januscoder-14B GGUF?
The files are on Hugging Face in the unsloth/JanusCoder-14B-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-14B 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‑14B on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with approximate memory usage of 5.7–5.9 GB at 8k context.
Does the model support vision in llama.cpp?
Vision support requires the --jinja flag; otherwise only text and coding tasks are available.
What license applies to this model?
The model is released under the apache‑2.0 license.