IN

InternVL3 78B Pretrained

InternvlGGUF by mradermacherUpdated 2025-08-31
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2
Smallest quant22.7 GB
Quick answer

InternVL3 78B Pretrained needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 20 quants, from 22.7 GB (IQ1_S) to 47.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

InternVL3 78B Pretrained – 72.7B multimodal LLM

InternVL3 78B Pretrained is a 72.7B parameter multimodal large language model. It supports coding and tool usage. The model is based on the qwen2 architecture and trained with a 32768 token context.

Good at

  • Coding tasks
  • Tool integration
  • Multimodal reasoning

Limits

  • No vision support in this text-only spec
  • Large memory requirement
  • License type is other

Best for

  • Developers building multimodal assistants
  • Researchers testing large vision-language models
  • Tool‑enabled coding workflows

Who it’s for. This model is suitable for users who need a large multimodal foundation model for experimentation or integration into custom applications. It is not a fine‑tuned or vision‑only model, so it requires additional setup for image processing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S22.7 GB 25.9 GB
Too big Get file →
IQ1_M23.7 GB 26.9 GB
Too big Get file →
IQ2_XXS25.5 GB 28.7 GB
Too big Get file →
IQ2_XS27.1 GB 30.2 GB
Too big Get file →
IQ2_S27.9 GB 31.1 GB
Too big Get file →
IQ2_M29.3 GB 32.5 GB
Too big Get file →
Q2_K_S29.6 GB 32.7 GB
Too big Get file →
Q2_K29.8 GB 33.0 GB
Too big Get file →
IQ3_XXS31.8 GB 35.0 GB
Too big Get file →
IQ3_XS32.8 GB 36.0 GB
Too big Get file →
IQ3_S34.5 GB 37.7 GB
Too big Get file →
Q3_K_S34.5 GB 37.7 GB
Too big Get file →
IQ3_M35.5 GB 38.7 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q3_K_L39.5 GB 42.7 GB
Too big Get file →
IQ4_XS39.7 GB 42.9 GB
Too big Get file →
Q4_041.4 GB 44.6 GB
Too big Get file →
Q4_K_S43.9 GB 47.1 GB
Too big Get file →
Q4_145.7 GB 48.9 GB
Too big Get file →
Q4_K_M47.4 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (22.69 GB file, 25.9 GB memory at 8k context). For 16 GB VRAM, IQ1_M (23.74 GB file, 26.9 GB memory). For 24 GB VRAM, IQ2_XS (27.05 GB file, 30.2 GB memory).

What GPU do you need for InternVL3 78B Pretrained?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ2_S (27.9 GB file, about 31.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).

Which InternVL3 78B Pretrained quant should you choose?

Q4_K_M is the usual starting point for InternVL3 78B Pretrained: it balances file size and quality well. Here it is a 47.4 GB file.

If memory is tight, the smallest file is IQ1_S at 22.7 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

Architectureqwen2
Parameters72.7B
Layers80
Trained context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyInternvl
Licenseother
Downloads (HF)1,015
Last updated2025-08-31

Frequently asked questions about InternVL3 78B Pretrained

How much VRAM does InternVL3 78B Pretrained need?

About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 78B Pretrained on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of InternVL3 78B Pretrained GGUF?

It depends on the quant: IQ1_S is 22.7 GB, IQ1_M is 23.7 GB, IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_S is 27.9 GB, IQ2_M is 29.3 GB and 14 more.

What context length does InternVL3 78B Pretrained support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download InternVL3 78B Pretrained GGUF?

The files are on Hugging Face in the mradermacher/InternVL3-78B-Pretrained-i1-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 78B Pretrained use?

Hugging Face lists the license as other. 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 78B on 8 GB VRAM?

Use the IQ1_S quant, which requires 25.9 GB memory at 8k context, so it will not fit on 8 GB VRAM.

Does this model support image input?

The provided GGUF files are for a vision model; image handling requires additional mmproj files not listed here.

What license applies to this model?

The license is listed as "other"; check the source repository for details.

Other GGUFs of InternVL3-78B-Pretrained

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Internvl models

All Internvl →

Other large models

All large models →