diffusiongemma-26B-A4B-it
Quantized verisons of google/diffusiongemma-26B-A4B-it
AI & ML interests
OpenSource and AI
Recent Activity
Red Hat AI validated models - March 2026
March 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Red Hat AI validated models - January 2026
January 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
NVFP4 Models
Red Hat AI validated models - September 2025
September 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Red Hat AI validated models - May 2025
May 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Docling Models
Gemma-3 Quantized
Collection of quantized Gemma 3 models created by Google.
Llama 4 Quantized
Quantized variants of the Llama 4 release by Meta.
Mistral-Small-3.1 (2503) Instruct Quantized
Quantized variants of Mistral Small 3.1 (2503) Instruct.
Llama 3.3 70B Instruct Quantized
Quantized variants of Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out).
Granite Quantized
Quantized Granite models from IBM Research.
Red Hat AI validated models - May 2026
May 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Red Hat AI validated models - February 2026
February 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Intel Xeon-compatible Models
Red Hat AI validated models - October 2025
October 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Speculator Models
Embedding Models
Embedding models act as the bridge between raw, unstructured data and the numerical, vector-based format needed for efficient retrieval in GenAI apps.
IBM-Nasa Geospatial Models
IBM and NASA have teamed up to create a family of AI foundation models for Earth called Prithvi.
Whisper Quantized
Collection of quantized whisper models created by OpenAI
Qwen3 Quantized
Collection of quantized Qwen 3 models from Alibaba Cloud.
Phi-4 Quantized
Quantized variants of Phi-4 family of small language and multi-modal models by Microsoft.
Qwen 2.5 Quantized
Quantized variants of Qwen 2.5 Instruct and Qwen VL models
vLLM Kernels
Collection of kernels from vLLM built using https://github.com/huggingface/kernel-builder
diffusiongemma-26B-A4B-it
Quantized verisons of google/diffusiongemma-26B-A4B-it
Red Hat AI validated models - May 2026
May 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Red Hat AI validated models - March 2026
March 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Red Hat AI validated models - February 2026
February 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Red Hat AI validated models - January 2026
January 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Intel Xeon-compatible Models
NVFP4 Models
Red Hat AI validated models - October 2025
October 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Red Hat AI validated models - September 2025
September 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Speculator Models
Red Hat AI validated models - May 2025
May 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
Embedding Models
Embedding models act as the bridge between raw, unstructured data and the numerical, vector-based format needed for efficient retrieval in GenAI apps.
Docling Models
IBM-Nasa Geospatial Models
IBM and NASA have teamed up to create a family of AI foundation models for Earth called Prithvi.
Gemma-3 Quantized
Collection of quantized Gemma 3 models created by Google.
Whisper Quantized
Collection of quantized whisper models created by OpenAI
Llama 4 Quantized
Quantized variants of the Llama 4 release by Meta.
Qwen3 Quantized
Collection of quantized Qwen 3 models from Alibaba Cloud.
Mistral-Small-3.1 (2503) Instruct Quantized
Quantized variants of Mistral Small 3.1 (2503) Instruct.
Phi-4 Quantized
Quantized variants of Phi-4 family of small language and multi-modal models by Microsoft.
Llama 3.3 70B Instruct Quantized
Quantized variants of Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out).
Qwen 2.5 Quantized
Quantized variants of Qwen 2.5 Instruct and Qwen VL models
Granite Quantized
Quantized Granite models from IBM Research.
vLLM Kernels
Collection of kernels from vLLM built using https://github.com/huggingface/kernel-builder