Internvl GGUF models

158 GGUF models in the Internvl family, quantized by 41 uploaders. Sizes run from 11M to 235B parameters. The longest trained context is 40K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
IN
InternVL3_5 8B
Internvl · bartowski
Params8.19B
Context40K
Q4_K_M5.0 GB
Vision
IN
InternVL3_5 2B
Internvl · bartowski
Params2.03B
Context40K
Q4_K_M1.3 GB
Vision
IN
InternVL3_5 14B
Internvl · bartowski
Params14.8B
Context40K
Q4_K_M9.0 GB
Vision
IN
InternVL3_5 30B A3B
Internvl · bartowski
Params30.5B
Context40K
Q4_K_M18.6 GB
Vision
IN
InternVL3_5 38B
Internvl · bartowski
Params32.8B
Context40K
Q4_K_M19.8 GB
Vision
IN
InternVL3_5 38B
Internvl · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
CodingVision
IN
InternVL3 1B Instruct
Internvl · ggml-org
Params630M
Context32K
Smallest0.7 GB
Vision
IN
InternVL3 8B Instruct
Internvl · ggml-org
Params7.61B
Context32K
Q4_K_M4.7 GB
Vision
IN
InternVL3_5 4B
Internvl · bartowski
Params4.41B
Context40K
Q4_K_M2.7 GB
Vision
IN
Internvl3-78B-Instruct
Internvl · unsloth
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingVision
IN
InternVL3_5 8B
Internvl · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingVision
IN
InternVL3_5 8B
Internvl · lmstudio-community
Params8.19B
Context40K
Q4_K_M5.0 GB
Vision
IN
Internvl3-8B
Internvl · unsloth
Params7.61B
Context32K
Q4_K_M4.7 GB
CodingVision
IN
InternVL3 2B Instruct
Internvl · ggml-org
Params1.78B
Context32K
Q4_K_M1.1 GB
Vision
IN
InternVL3_5 1B
Internvl · bartowski
Params752M
Context40K
Q4_K_M0.5 GB
Vision
IN
InternVL3 78B Instruct
Internvl · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool use
IN
InternVL3_5 8B
Internvl · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Coding
IN
InternVL3_5 4B
Internvl · mradermacher
Params4.41B
Context40K
Q4_K_M2.7 GB
CodingVision
IN
Internvl3-2B
Internvl · unsloth
Params1.78B
Context32K
Q4_K_M1.1 GB
CodingVision
IN
InternVL3_5 2B
Internvl · lmstudio-community
Params2.03B
Context40K
Q4_K_M1.3 GB
Vision
IN
InternVL3 14B Instruct
Internvl · ggml-org
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool useVision
IN
Internvl3-14B-Instruct
Internvl · unsloth
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingVision
IN
Internvl3-1B-Instruct
Internvl · unsloth
Params630M
Context32K
Q4_K_M0.5 GB
CodingVision
IN
InternVL2_5 78B
Internvl · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool use
IN
InternVL2_5 1B
Internvl · ggml-org
Params630M
Context32K
Smallest0.7 GB
Tool useVision
IN
InternVL3_5 14B
Internvl · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingVision
IN
InternVL3 78B Pretrained
Internvl · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool use
IN
Internvl3-2B-Instruct
Internvl · unsloth
Params1.78B
Context32K
Q4_K_M1.1 GB
CodingTool useVision
IN
Internvl3-1B
Internvl · unsloth
Params630M
Context32K
Q4_K_M0.5 GB
CodingTool useVision
IN
InternVL3_5 14B
Internvl · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
Coding

About the Internvl GGUF models

Internvl is represented on ggufmodels.com by 158 GGUF models, quantized by 41 uploaders on Hugging Face. The most downloaded are InternVL3_5 8B, InternVL3_5 2B and InternVL3_5 14B. Parameter counts run from 11M to 235B, and the longest trained context window is 40K tokens.

A Q4_K_M file of a Internvl model is between 0.5 to 47.4 GB, which is the quant most people start with. Most files come from mradermacher (67), unsloth (12) and bartowski (7). The quants you will meet most often are Q4_K_M (121), Q4_K_S (93), Q3_K_S (92) and Q3_K_M (92), where the number is how many models offer that quant.

Frequently asked questions

Which Internvl GGUF should I download?

The most downloaded Internvl GGUF here is InternVL3_5 8B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Internvl model need?

Q4_K_M files of Internvl models on this site range from 0.5 to 47.4 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Internvl GGUF files come from?

The most common quantizers here are mradermacher, unsloth and bartowski. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing