InternVL3 14B Instruct needs about 11.1 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 3 quants, from 9.0 GB (Q4_K_M) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
InternVL3 14B Instruct – multimodal LLM with tool and vision support
InternVL3 14B Instruct is a 14.8 billion‑parameter multimodal model based on the Qwen2 architecture. It supports vision, text, and tool usage. The model is released under the Apache‑2.0 license.
Good at
- Vision‑text reasoning
- Tool‑enabled interactions
- Multimodal instruction following
Limits
- Requires 32768 token context
- No native video support
- No vision‑only inference without image input
Best for
- Image‑based question answering
- GUI automation scripts
- Multimodal chat assistants
Who it’s for. Developers building multimodal applications that need tool integration and high‑quality vision reasoning. Researchers exploring multimodal instruction following can use this model for experiments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 9.0 GB | 11.1 GB | Too big | Get file → | |
| Q8_0 | 15.7 GB | 17.8 GB | Too big | Get file → | |
| F16 | 29.5 GB | 31.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (8.99 GB file, ~11.1 GB memory at 8k context). For 16 GB VRAM, Q8_0 (15.7 GB file, ~17.8 GB memory). For 32 GB VRAM, F16 (29.54 GB file, ~31.7 GB memory).
What GPU do you need for InternVL3 14B Instruct?
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 Q4_K_M (9.0 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (9.0 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.8 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (29.5 GB file, about 31.7 GB in use).
Which InternVL3 14B Instruct quant should you choose?
Q4_K_M is the usual starting point for InternVL3 14B Instruct: 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about InternVL3 14B Instruct
How much VRAM does InternVL3 14B Instruct need?
About 11.1 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 InternVL3 14B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of InternVL3 14B Instruct GGUF?
It depends on the quant: Q4_K_M is 9.0 GB, Q8_0 is 15.7 GB, F16 is 29.5 GB.
What context length does InternVL3 14B Instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download InternVL3 14B Instruct GGUF?
The files are on Hugging Face in the ggml-org/InternVL3-14B-Instruct-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 InternVL3 14B Instruct 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 InternVL3 14B Instruct on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 11.1 GB of VRAM at 8k context.
Does the model support video input?
No, the current version supports only images and text.
What license applies to this model?
The model is released under the Apache‑2.0 license.