IN

InternVL3 8B Instruct

InternvlGGUF by ggml-orgUpdated 2025-05-10
Download on Hugging Face
Parameters7.61B
Context32K
Layers28
Architectureqwen2
Smallest quant4.7 GB
Quick answer

InternVL3 8B Instruct needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 4.7 GB (Q4_K_M) to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

InternVL3 8B Instruct – multimodal LLM with vision support

InternVL3 8B Instruct is a 7.61 billion parameter model that supports vision and text. It is trained with a 32768‑token context window and released under the apache‑2.0 license. The model is available in several GGUF quantizations.

Good at

  • Vision‑text reasoning
  • Multi‑image and video inputs
  • Tool usage and GUI agent tasks

Limits

  • No vision support in lower‑ranked quantizations
  • Requires large VRAM for full precision
  • No MPO training applied

Best for

  • Image captioning
  • Multimodal question answering
  • Video analysis

Who it’s for. Developers building multimodal applications that need both vision and language understanding. The model is suitable for research and production use where an open‑source license is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →
F1615.2 GB 16.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.68 GB, ~5.7 GB memory at 8k context). For 12 GB VRAM, Q8_0 (8.1 GB, ~9.1 GB memory). Full precision F16 requires 15.23 GB and ~16.2 GB memory, suitable for high‑end GPUs.

What GPU do you need for InternVL3 8B 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: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.2 GB file, about 16.2 GB in use).

Which InternVL3 8B Instruct quant should you choose?

Q4_K_M is the usual starting point for InternVL3 8B Instruct: it balances file size and quality well. Here it is a 4.7 GB file.

The Q8_0 file is 8.1 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

Architectureqwen2
Parameters7.61B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byggml-org
FamilyInternvl
Licenseapache-2.0
Downloads (HF)3,335
Last updated2025-05-10

Frequently asked questions about InternVL3 8B Instruct

How much VRAM does InternVL3 8B Instruct need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 8B Instruct on an 8 GB GPU?

Yes, with Q4_K_M: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of InternVL3 8B Instruct GGUF?

It depends on the quant: Q4_K_M is 4.7 GB, Q8_0 is 8.1 GB, F16 is 15.2 GB.

What context length does InternVL3 8B 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 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download InternVL3 8B Instruct GGUF?

The files are on Hugging Face in the ggml-org/InternVL3-8B-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 8B 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 8B Instruct on 8 GB VRAM?

Yes, the Q4_K_M quantization is 4.68 GB and uses about 5.7 GB of VRAM at 8k context.

Does this model support video input?

Yes, InternVL3 supports multi‑image and video data as part of its architecture.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of InternVL3-8B-Instruct

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Internvl models

All Internvl →

Other small models

All small models →