8B multimodal model on Qwen3-8B and SigLIP2-400M for single-image, multi-image and high-FPS video understanding, OCR and document parsing.

size

8B

vram

~7 GB

license

Apache-2.0

#vision

Mistral Small 3.1 update with better instruction following, fewer repetitive outputs and more robust function calling; text and image input.

size

24B

vram

~17 GB

license

Apache-2.0

#chat #instruct #vision

Hunyuan3D-2.1: the highest-fidelity shapes of the family, from a 3.3B model, with fully open training code.

size

3.3B

vram

~10 GB

license

Tencent Hunyuan Community

#3d #image-to-3d #high-fidelity

Hunyuan3D-2 with the turbo shape model: full-size 2.0 quality in a handful of steps, using FlashVDM decoding.

size

1.1B

vram

~6 GB

license

Tencent Hunyuan Community

#3d #image-to-3d #fast

Hunyuan3D-2 mini, guidance-distilled: about half the compute per step with nearly the same shapes. The middle ground between mini and mini-turbo.

size

0.6B

vram

~5 GB

license

Tencent Hunyuan Community

#3d #image-to-3d #fast

Hunyuan3D-2 mini turns a single image into a clean 3D mesh. 0.6B parameters — the smallest Hunyuan shape model, and the one to start with.

size

0.6B

vram

~5 GB

license

Tencent Hunyuan Community

#3d #image-to-3d #mesh

Mistral Small 3.1 24B: fast general model with image understanding and 128K context, under Apache-2.0.

size

24B

vram

~16 GB

license

Apache-2.0

#vision #chat #tools

Gemma 3: 1B to 27B, with image understanding from 4B up, 128K context and 140+ languages.

size

12B

vram

~9 GB

license

Gemma

#vision #chat #multilingual

Google's multimodal Gemma 3 4B instruction-tuned model: text and image input, text output, 128K context, 140+ languages.

size

4B

vram

~5 GB

license

Gemma

#chat #instruct #vision

Google's multimodal Gemma 3 27B instruction-tuned model: text and image input, text output, 128K context, 140+ languages.

size

27B

vram

~19 GB

license

Gemma

#chat #instruct #vision

Lightweight multimodal model that processes video, image and text inputs to generate text; about 5.2GB of GPU RAM for video inference.

size

2.2B

vram

~4 GB

license

Apache-2.0

#vision #small

Qwen2.5-VL: reads documents, charts, screenshots and photos, and can point to things in an image.

size

7B

vram

~6 GB

license

Apache-2.0

#vision #ocr #documents

The full-size Hunyuan3D-2.0: a 1.1B shape model plus a paint model that textures the mesh from the same image.

size

1.1B

vram

~6 GB

license

Tencent Hunyuan Community

#3d #image-to-3d #texture

Stable Diffusion 3.5 Large — a powerful 8B text-to-image model with improved typography and photorealism.

size

8B

vram

~16 GB

license

Stability AI Community

#image #text-to-image #photorealism

FLUX.1 [schnell] — a fast, fully open (Apache-2.0) text-to-image model that generates high-quality images in just 1–4 steps.

size

12B

vram

~24 GB

license

Apache-2.0

#image #text-to-image #fast

FLUX.1 [dev] — a 12B text-to-image model with exceptional quality and prompt adherence (non-commercial license).

size

12B

vram

~24 GB

license

FLUX.1 [dev] Non-Commercial

#image #text-to-image #high-quality

Stable Diffusion XL — the widely-used open text-to-image model with a huge ecosystem of fine-tunes and LoRAs.

size

3.5B

vram

~8 GB

license

OpenRAIL++-M

#image #text-to-image #loras

TripoSR reconstructs a 3D mesh from one image in a single feed-forward pass — under a second on a GPU. Rougher than Hunyuan, but instant.

size

0.4B

vram

~6 GB

license

MIT

#3d #image-to-3d #fast