Llama JoyCaption Alpha Two needs about 8.2 GB of memory at Q6_K (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.6 GB (Q6_K) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
8.03B Llama VLM for image captioning
Llama JoyCaption Alpha Two is an 8.03B parameter visual language model. It supports vision and tools, trained on 131072 context tokens. The model is released as free, open weights with no restrictions.
Good at
- Image captioning
- Vision‑language tasks
- Tool usage
Limits
- No vision support in some runtimes
- Large VRAM requirement for full quant
- License not specified
Best for
- Generating captions for training diffusion models
- Automated image description
- Fine‑tuning VLMs
Who it’s for. Developers and researchers needing an unrestricted VLM for image captioning. The model is suitable for those building or training diffusion models and requiring high‑quality captions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 6.6 GB | 8.2 GB | Too big | Get file → | |
| F16 | 16.1 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q6_K (file size 6.6 GB, estimated 8.2 GB memory at 8 k context). For 16 GB VRAM, F16 (16.07 GB, 17.6 GB memory) is available. Estimates are approximate.
What GPU do you need for Llama JoyCaption Alpha Two?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).
Which Llama JoyCaption Alpha Two quant should you choose?
Q6_K (6.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama JoyCaption Alpha Two
How much VRAM does Llama JoyCaption Alpha Two need?
About 8.2 GB at Q6_K with an 8K context window. That is the 6.6 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 Llama JoyCaption Alpha Two on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama JoyCaption Alpha Two GGUF?
It depends on the quant: Q6_K is 6.6 GB, F16 is 16.1 GB.
What context length does Llama JoyCaption Alpha Two support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Llama JoyCaption Alpha Two GGUF?
The files are on Hugging Face in the Jobaar/Llama-JoyCaption-Alpha-Two-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Llama JoyCaption Alpha Two on 8 GB VRAM?
Yes, the Q6_K quantization requires about 8.2 GB memory at 8 k context, which fits an 8 GB GPU with some headroom.
Does the model support vision tasks?
Yes, it has detected vision ability and is designed for image captioning.
Is the model free to use?
The model is released with free, open weights and no restrictions, as stated in its documentation.