Llama Joycaption Beta One Hf Llava needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.2 GB (Q2_K) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
8B Llama VLM for image captioning
Llama Joycaption Beta One is an 8‑billion‑parameter visual language model trained for image captioning. It supports vision input and generates descriptive text. The model is free, open, and uncensored.
Good at
- Image captioning
- Visual content description
- Unrestricted text generation
Limits
- No vision support beyond image captioning
- Large VRAM needed for higher quant
- License not specified
Best for
- Captioning datasets for diffusion training
- Generating training data for text‑to‑image models
- Automated image description in applications
Who it’s for. Developers and researchers needing a free, open VLM for image captioning. Suitable for building diffusion training pipelines or adding captioning to applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_S | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q5_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| F16 | 16.1 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_S (3.66 GB, ~5.2 GB RAM). For 12 GB VRAM, Q4_K_S (4.69 GB, ~6.3 GB RAM) or Q4_K_M (4.92 GB, ~6.5 GB RAM). Higher quants give better quality but require more memory.
What GPU do you need for Llama Joycaption Beta One Hf Llava?
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 Q3_K_L (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 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 Beta One Hf Llava quant should you choose?
Q4_K_M is the usual starting point for Llama Joycaption Beta One Hf Llava: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.5 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 3.2 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
Frequently asked questions about Llama Joycaption Beta One Hf Llava
How much VRAM does Llama Joycaption Beta One Hf Llava need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Beta One Hf Llava on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama Joycaption Beta One Hf Llava GGUF?
It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, IQ4_XS is 4.5 GB, Q4_K_S is 4.7 GB and 6 more.
What context length does Llama Joycaption Beta One Hf Llava 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 Beta One Hf Llava GGUF?
The files are on Hugging Face in the mradermacher/llama-joycaption-beta-one-hf-llava-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 Beta One on 8 GB VRAM?
Yes, with the Q3_K_S quant it uses about 5.2 GB of VRAM at 8k context.
Does the model support text‑to‑image generation?
No, it is a captioning VLM; it does not generate images.
Is the model censored?
No, it is uncensored and covers both SFW and NSFW content.