llava phi 3 mini needs about 6.0 GB of memory at its main file (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.3 GB to 7.6 GB (F16).
llava phi 3 mini – a vision‑enabled LLaMA model in GGUF format
llava phi 3 mini is a 3.82B parameter LLaMA model fine‑tuned for vision tasks. It supports 4096 context tokens and is available in GGUF format. The model is built on microsoft/Phi-3-mini-4k-instruct and CLIP-ViT-Large-patch14-336.
Good at
- Vision‑enabled text generation
- Image captioning
- Multimodal dialogue
Limits
- No vision support beyond image input
- Requires 8k context for full capability
- License not specified
Best for
- Rapid prototyping of multimodal apps
- Educational demos of vision LLMs
- Low‑resource inference on local hardware
Who it’s for. Developers and researchers needing a lightweight vision‑enabled LLaMA model for local inference. The model is suitable for environments with limited GPU memory and for quick experimentation with multimodal prompts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.3 GB | 4.4 GB | Fits | Get file → | |
| F16 | 7.6 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, use the 2.32 GB unknown‑quant file; it requires about 6 GB memory at 8k context. If more memory is available, the 7.64 GB F16 file uses about 11.4 GB at 8k context. These estimates are approximate.
What GPU do you need for llava phi 3 mini?
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 (2.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (2.3 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about llava phi 3 mini
How much VRAM does llava phi 3 mini need?
About 6.0 GB at its main file with an 8K context window. That is the 2.3 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 llava phi 3 mini on an 8 GB GPU?
Yes, with the smaller files: the 2.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of llava phi 3 mini GGUF?
It depends on the quant: file is 2.3 GB, F16 is 7.6 GB.
What context length does llava phi 3 mini support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.
Where can I download llava phi 3 mini GGUF?
The files are on Hugging Face in the xtuner/llava-phi-3-mini-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 llava phi 3 mini on 8 GB VRAM?
Yes, the 2.32 GB unknown‑quant file should fit within 8 GB VRAM, using roughly 6 GB at 8k context.
What context length does the model support?
The model was trained with 4096 context tokens and performs best with that length.
Does the model support vision tasks?
Yes, it has detected vision abilities and is fine‑tuned for image‑based prompts.