LIVE

Publisher profile

ggml-org AI models

Explore active AI models attributed to ggml-org across indexed source catalogs. Open any profile for capabilities, context, pricing and verified source links.

Models
18
Categories
4
Sources
1
visionreasoningaudiovideo

Available catalog

Published models

18 active

Hugging Face↗

Clef-Flash-GGUF

Clef-Flash-GGUF is a Hugging Face model repository for image text to text under the apache-2.0 license.

visiontextimage
Size
Size not listed
Context
Not listed
Hugging Face↗

DeepSeek-V4-Flash-0731-GGUF

DeepSeek-V4-Flash-0731-GGUF AI model directory entry.

text
Size
Size not listed
Context
Not listed
Hugging Face↗

DeepSeek-V4-Flash-GGUF

DeepSeek-V4-Flash-GGUF AI model directory entry.

text
Size
Size not listed
Context
Not listed
Hugging Face↗

embeddinggemma-300M-GGUF

embeddinggemma-300M-GGUF is a 300 million-parameter GGUF-format embedding model, mainly useful for converting text into vector representations for semantic search, retrieval, clustering, recommendation, and other similarity-based applications. The directory record identifies its base model as Google’s embeddinggemma-300m and indicates compatibility with supported endpoints, with a US region capability. Because it is an embedding model rather than a general-purpose text-generation model, developers should evaluate it for vector quality and retrieval behavior rather than chat, coding, or generation tasks. The available source material does not disclose a context-window size, inference-speed benchmark, pricing, input or output modalities, or detailed embedding dimensions. It also does not provide model-card guidance on licensing, safety, training data, supported languages, normalization, or production deployment requirements, so those details should be verified before adoption. No performance rankings or benchmark results are reported in the supplied source. The source is the model repository on Hugging Face under the ggml-org organization; the provided page snapshot confirms the repository identity and canonical URL but does not expose a dated release or update note, so repository metadata should be checked for the latest files and documentation.

Size
300M parameters
Context
Not listed
Hugging Face↗

gemma-4-12B-it-GGUF

Model card indexed from Hugging Face for any-to-any.

Size
12B parameters
Context
Not listed
Hugging Face↗

GLM-4.5-Air-GGUF

Model card indexed from Hugging Face for text-generation.

text
Size
Size not listed
Context
Not listed
Hugging Face↗

gpt-oss-120b-GGUF

gpt-oss-120b-GGUF is an AI model record indexed from Hugging Face.

text
Size
120B parameters
Context
Not listed
Hugging Face↗

Laguna-S-2.1-GGUF

Laguna-S-2.1-GGUF AI model directory entry.

text
Size
Size not listed
Context
Not listed
Hugging Face↗

LongCat-Flash-Chat-GGUF

Model card indexed from Hugging Face.

Size
Size not listed
Context
Not listed
Hugging Face↗

NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF

Model card indexed from Hugging Face for text-generation.

text
Size
30B parameters
Context
Not listed
Hugging Face↗

NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-GGUF

Model card indexed from Hugging Face for any-to-any.

reasoning
Size
30B parameters
Context
Not listed
Hugging Face↗

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF

Model card indexed from Hugging Face.

Size
30B parameters
Context
Not listed
Hugging Face↗

Qwen3-8B-Base-GGUF

Qwen3-8B-Base-GGUF is an AI model record indexed from Hugging Face.

text
Size
8B parameters
Context
Not listed
Hugging Face↗

Qwen3-8B-GGUF

Qwen3-8B-GGUF is an AI model record indexed from Hugging Face.

text
Size
8B parameters
Context
Not listed
Hugging Face↗

Qwen3-TTS-12Hz-1.7B-Base-GGUF

Qwen3-TTS-12Hz-1.7B-Base-GGUF is an AI model record indexed from Hugging Face.

audio
Size
1.7B parameters
Context
Not listed
Hugging Face↗

Qwen3.8-27B-GGUF

Model card indexed from Hugging Face for image-text-to-text.

visionimagetext
Size
27B parameters
Context
Not listed
Hugging Face↗

Qwen3.8-Flash-Next-GGUF

Model card indexed from Hugging Face for image-text-to-text.

visionimagetext
Size
Size not listed
Context
Not listed
Hugging Face↗

SmolVLM2-256M-Video-Instruct-GGUF

Model card indexed from Hugging Face for image-text-to-text.

visionvideoimagetext
Size
256M parameters
Context
Not listed

Continue exploring

Related guides and tools