IN

InternVL3_5 2B

InternvlGGUF by bartowskiUpdated 2025-08-26
Download on Hugging Face
Parameters2.03B
Context40K
Layers28
Architectureqwen3
Smallest quant0.0 GB
Quick answer

InternVL3_5 2B needs about 2.7 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 4.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

InternVL3_5 2B – a 2‑billion‑parameter vision‑language model

InternVL3_5 2B is a 2‑billion‑parameter multimodal model based on the Qwen3 architecture. It supports vision input and was trained with a context length of 40,960 tokens. The model is released under the Apache‑2.0 license and is available in multiple GGUF quantizations.

Good at

  • Vision‑language reasoning
  • Dynamic visual resolution routing
  • Decoupled vision‑language deployment

Limits

  • No text‑only support
  • Requires 8‑k context for estimates
  • Large VRAM needed for higher quants

Best for

  • Image captioning with context
  • Multimodal QA in research settings
  • Embedding extraction for vision tasks

Who it’s for. Researchers and developers needing a lightweight vision‑language model for inference on consumer GPUs. The model is suitable for applications that require reasoning over images and text with a moderate memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
IQ2_M0.8 GB 2.3 GB
Fits Get file →
Q2_K0.9 GB 2.3 GB
Fits Get file →
IQ3_XXS0.9 GB 2.3 GB
Fits Get file →
IQ3_XS1.0 GB 2.4 GB
Fits Get file →
Q3_K_S1.0 GB 2.4 GB
Fits Get file →
IQ3_M1.0 GB 2.5 GB
Fits Get file →
Q3_K_M1.1 GB 2.5 GB
Fits Get file →
Q3_K_L1.1 GB 2.6 GB
Fits Get file →
IQ4_XS1.2 GB 2.6 GB
Fits Get file →
Q2_K_L1.2 GB 2.6 GB
Fits Get file →
IQ4_NL1.2 GB 2.7 GB
Fits Get file →
Q4_01.2 GB 2.7 GB
Fits Get file →
Q4_K_S1.2 GB 2.7 GB
Fits Get file →
Q4_K_M1.3 GB 2.7 GB
Fits Get file →
Q4_11.3 GB 2.8 GB
Fits Get file →
Q3_K_XL1.4 GB 2.8 GB
Fits Get file →
Q5_K_S1.4 GB 2.9 GB
Fits Get file →
Q5_K_M1.5 GB 2.9 GB
Fits Get file →
Q4_K_L1.5 GB 3.0 GB
Fits Get file →
Q5_K_L1.7 GB 3.1 GB
Fits Get file →
Q6_K1.7 GB 3.1 GB
Fits Get file →
Q6_K_L1.8 GB 3.3 GB
Fits Get file →
Q8_02.2 GB 3.6 GB
Fits Get file →
BF164.1 GB 5.5 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 (1.23 GB file, ~2.7 GB memory). With 12 GB VRAM, Q5_K_M (1.47 GB file, ~2.9 GB memory) is a good balance. For 16 GB VRAM, Q6_K_L (1.82 GB file, ~3.3 GB memory) offers higher quality.

What GPU do you need for InternVL3_5 2B?

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: the best quant that fits is Q8_0 (2.2 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (4.1 GB file, about 5.5 GB in use).

Which InternVL3_5 2B quant should you choose?

Q4_K_M is the usual starting point for InternVL3_5 2B: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.2 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters2.03B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized bybartowski
FamilyInternvl
Licenseapache-2.0
Downloads (HF)6,136
Last updated2025-08-26

Frequently asked questions about InternVL3_5 2B

How much VRAM does InternVL3_5 2B need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.3 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 InternVL3_5 2B on an 8 GB GPU?

Yes, with BF16: the 4.1 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of InternVL3_5 2B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 0.8 GB, Q2_K is 0.9 GB, IQ3_XXS is 0.9 GB, IQ3_XS is 1.0 GB, Q3_K_S is 1.0 GB and 19 more.

What context length does InternVL3_5 2B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download InternVL3_5 2B GGUF?

The files are on Hugging Face in the bartowski/OpenGVLab_InternVL3_5-2B-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_5 2B 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_5 2B on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 2.7 GB of VRAM at 8‑k context.

Does the model support text‑only inference?

No, InternVL3_5 2B is a vision‑language model and requires image input for full functionality.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of InternVL3_5-2B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Internvl models

All Internvl →

Other tiny models

All tiny models →