IN

InternVL3 38B Instruct

InternvlGGUF by mradermacherUpdated 2025-08-31
Download on Hugging Face
Parameters32.8B
Context32K
Layers64
Architectureqwen2
Smallest quant7.3 GB
Quick answer

InternVL3 38B Instruct needs about 22.5 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 7.3 GB (IQ1_S) to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

InternVL3 38B Instruct – a multimodal LLM with 32.8B parameters

InternVL3 38B Instruct is a vision‑language model based on the qwen2 architecture. It supports coding and tool usage and was trained with a 32768 token context window. The model is released under the apache‑2.0 license.

Good at

  • Multimodal reasoning
  • Tool and GUI agent support
  • Large context handling

Limits

  • No vision support in this GGUF version
  • Requires large VRAM for higher‑quality quants
  • No MPO training

Best for

  • Developing multimodal assistants
  • Image‑based code generation
  • Complex reasoning tasks

Who it’s for. Engineers and researchers building multimodal applications who need a large context window and tool‑usage capabilities. The model is suitable for those who can allocate sufficient GPU memory for the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.3 GB 9.9 GB
Too big Get file →
IQ1_M7.9 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.4 GB 13.0 GB
Too big Get file →
IQ2_M11.3 GB 13.9 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.8 GB 17.5 GB
Too big Get file →
Q3_K_M15.9 GB 18.6 GB
Too big Get file →
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.8 GB 22.5 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.3 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 7.27 GB, estimated 9.9 GB memory). For 12 GB VRAM, IQ1_M (7.93 GB, 10.6 GB). For 16 GB VRAM, IQ2_XS (9.96 GB, 12.6 GB). Higher quants require proportionally more memory.

What GPU do you need for InternVL3 38B 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 IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which InternVL3 38B Instruct quant should you choose?

Q4_K_M is the usual starting point for InternVL3 38B Instruct: it balances file size and quality well. Here it is a 19.8 GB file.

If memory is tight, the smallest file is IQ1_S at 7.3 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
Parameters32.8B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyInternvl
Licenseapache-2.0
Downloads (HF)554
Last updated2025-08-31

Frequently asked questions about InternVL3 38B Instruct

How much VRAM does InternVL3 38B Instruct need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.8 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 38B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of InternVL3 38B Instruct GGUF?

It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB and 17 more.

What context length does InternVL3 38B 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 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download InternVL3 38B Instruct GGUF?

The files are on Hugging Face in the mradermacher/InternVL3-38B-Instruct-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 38B 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 38B Instruct on 8 GB VRAM?

Use the IQ1_S quant; it requires about 9.9 GB of VRAM at 8 k context.

Does this model support vision tasks?

The GGUF files are vision‑enabled; mmproj files are included in the static repository.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of InternVL3-38B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Internvl models

All Internvl →

Other medium models

All medium models →