March 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
AI & ML interests
OpenSource and AI
Recent Activity
View all activity
January 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
October 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/gpt-oss-120b
Text Generation • 120B • Updated • 866 • 4 -
RedHatAI/gpt-oss-20b
Text Generation • 22B • Updated • 21.6k • 5 -
RedHatAI/Qwen3-Coder-480B-A35B-Instruct-FP8
Text Generation • 480B • Updated • 128 • 3 -
RedHatAI/whisper-large-v3-turbo-quantized.w4a16
Automatic Speech Recognition • 0.2B • Updated • 426 • 7
-
RedHatAI/Llama-3.1-8B-Instruct-speculator.eagle3
Text Generation • 1.0B • Updated • 18.4k • 2 -
RedHatAI/Llama-3.3-70B-Instruct-speculator.eagle3
Text Generation • 2B • Updated • 325 • 1 -
RedHatAI/Qwen3-8B-speculator.eagle3
Text Generation • 1B • Updated • 86.8k • 2 -
RedHatAI/Qwen3-14B-speculator.eagle3
Text Generation • 1B • Updated • 610
Embedding models act as the bridge between raw, unstructured data and the numerical, vector-based format needed for efficient retrieval in GenAI apps.
IBM and NASA have teamed up to create a family of AI foundation models for Earth called Prithvi.
Collection of quantized whisper models created by OpenAI
-
RedHatAI/whisper-large-v3-turbo-quantized.w4a16
Automatic Speech Recognition • 0.2B • Updated • 426 • 7 -
RedHatAI/whisper-large-v3-turbo-quantized.w8a8
Automatic Speech Recognition • 0.9B • Updated • 108 • 4 -
RedHatAI/whisper-large-v3-turbo-FP8-dynamic
Automatic Speech Recognition • 0.9B • Updated • 195 • 6 -
RedHatAI/whisper-tiny-FP8-Dynamic
Automatic Speech Recognition • 57.8M • Updated • 5
Collection of quantized Qwen 3 models from Alibaba Cloud.
-
RedHatAI/Qwen3-4B-quantized.w4a16
Text Generation • 1B • Updated • 13.5k • 4 -
RedHatAI/Qwen3-32B-FP8-dynamic
Text Generation • 33B • Updated • 8.11k • 15 -
RedHatAI/Qwen3-0.6B-FP8-dynamic
Text Generation • 0.8B • Updated • 1.55k • 1 -
RedHatAI/Qwen3-8B-FP8-dynamic
Text Generation • 8B • Updated • 19.7k • 12
Quantized variants of Phi-4 family of small language and multi-modal models by Microsoft.
Quantized variants of Qwen 2.5 Instruct and Qwen VL models
-
RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w8a8
Image-Text-to-Text • 8B • Updated • 45.7k • 9 -
RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w4a16
Image-Text-to-Text • 3B • Updated • 2.27k • 8 -
RedHatAI/Qwen2.5-7B-quantized.w8a8
Text Generation • 8B • Updated • 5 • 1 -
RedHatAI/Qwen2.5-VL-72B-Instruct-FP8-dynamic
Image-Text-to-Text • 73B • Updated • 1.99k • 15
Collection of kernels from vLLM built using https://github.com/huggingface/kernel-builder
February 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/Phi-4-reasoning-FP8-dynamic
Text Generation • 15B • Updated • 430 • 1 -
RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4
Text Generation • 133B • Updated • 13.5k • 15 -
RedHatAI/Qwen3-Next-80B-A3B-Instruct-quantized.w4a16
Text Generation • 12B • Updated • 289 • 3 -
RedHatAI/granite-4.0-h-tiny-FP8-dynamic
Text Generation • 7B • Updated • 555 • 2
-
RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4
Text Generation • 14B • Updated • 14.3k • 6 -
RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4
Text Generation • 133B • Updated • 13.5k • 15 -
RedHatAI/Qwen3-235B-A22B-Instruct-2507-NVFP4
Text Generation • 136B • Updated • 694 • 4 -
RedHatAI/Qwen3-235B-A22B-NVFP4
Text Generation • 136B • Updated • 24 • 1
September 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/DeepSeek-R1-0528-quantized.w4a16
Text Generation • 104B • Updated • 48 • 13 -
RedHatAI/Qwen3-8B-FP8-dynamic
Text Generation • 8B • Updated • 19.7k • 12 -
RedHatAI/Kimi-K2-Instruct-quantized.w4a16
Text Generation • 146B • Updated • 3.01k • 12 -
RedHatAI/gemma-3n-E4B-it-FP8-dynamic
Text Generation • 8B • Updated • 897 • 3
May 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic
Image-Text-to-Text • 109B • Updated • 11.9k • 28 -
RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16
Image-Text-to-Text • 20B • Updated • 7.64k • 12 -
RedHatAI/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • 109B • Updated • 10.4k -
RedHatAI/Llama-4-Maverick-17B-128E-Instruct
Image-Text-to-Text • 402B • Updated • 6 • 3
Collection of quantized Gemma 3 models created by Google.
-
RedHatAI/gemma-3-27b-it-quantized.w4a16
Image-Text-to-Text • 7B • Updated • 58.7k • 13 -
RedHatAI/gemma-3-12b-it-quantized.w4a16
Image-Text-to-Text • 4B • Updated • 13.4k • 3 -
RedHatAI/gemma-3-4b-it-quantized.w4a16
Image-Text-to-Text • 2B • Updated • 1.2k • 5 -
RedHatAI/gemma-3-1b-it-quantized.w8a8
Text Generation • 1B • Updated • 791 • 1
Quantized variants of the Llama 4 release by Meta.
-
RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic
Image-Text-to-Text • 109B • Updated • 11.9k • 28 -
RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16
Image-Text-to-Text • 20B • Updated • 7.64k • 12 -
RedHatAI/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 17.4k • 2 -
RedHatAI/Llama-4-Maverick-17B-128E-Instruct-quantized.w4a16
Image-Text-to-Text • 59B • Updated • 126 • 1
Quantized variants of Mistral Small 3.1 (2503) Instruct.
-
RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic
Image-Text-to-Text • 24B • Updated • 3.25k • 9 -
RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8
Image-Text-to-Text • 24B • Updated • 305 • 5 -
RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16
Image-Text-to-Text • 5B • Updated • 2.51k • 10
Quantized variants of Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out).
Quantized Granite models from IBM Research.
-
RedHatAI/granite-3.1-8b-instruct-quantized.w8a8
Text Generation • 8B • Updated • 177 • 2 -
RedHatAI/granite-3.1-2b-base-quantized.w8a8
Text Generation • 3B • Updated • 6 -
RedHatAI/granite-3.1-8b-instruct-quantized.w4a16
Text Generation • 1B • Updated • 789 • 1 -
RedHatAI/granite-3.1-2b-instruct-quantized.w8a8
Text Generation • 3B • Updated • 28
March 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
February 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/Phi-4-reasoning-FP8-dynamic
Text Generation • 15B • Updated • 430 • 1 -
RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4
Text Generation • 133B • Updated • 13.5k • 15 -
RedHatAI/Qwen3-Next-80B-A3B-Instruct-quantized.w4a16
Text Generation • 12B • Updated • 289 • 3 -
RedHatAI/granite-4.0-h-tiny-FP8-dynamic
Text Generation • 7B • Updated • 555 • 2
January 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4
Text Generation • 14B • Updated • 14.3k • 6 -
RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4
Text Generation • 133B • Updated • 13.5k • 15 -
RedHatAI/Qwen3-235B-A22B-Instruct-2507-NVFP4
Text Generation • 136B • Updated • 694 • 4 -
RedHatAI/Qwen3-235B-A22B-NVFP4
Text Generation • 136B • Updated • 24 • 1
October 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/gpt-oss-120b
Text Generation • 120B • Updated • 866 • 4 -
RedHatAI/gpt-oss-20b
Text Generation • 22B • Updated • 21.6k • 5 -
RedHatAI/Qwen3-Coder-480B-A35B-Instruct-FP8
Text Generation • 480B • Updated • 128 • 3 -
RedHatAI/whisper-large-v3-turbo-quantized.w4a16
Automatic Speech Recognition • 0.2B • Updated • 426 • 7
September 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/DeepSeek-R1-0528-quantized.w4a16
Text Generation • 104B • Updated • 48 • 13 -
RedHatAI/Qwen3-8B-FP8-dynamic
Text Generation • 8B • Updated • 19.7k • 12 -
RedHatAI/Kimi-K2-Instruct-quantized.w4a16
Text Generation • 146B • Updated • 3.01k • 12 -
RedHatAI/gemma-3n-E4B-it-FP8-dynamic
Text Generation • 8B • Updated • 897 • 3
-
RedHatAI/Llama-3.1-8B-Instruct-speculator.eagle3
Text Generation • 1.0B • Updated • 18.4k • 2 -
RedHatAI/Llama-3.3-70B-Instruct-speculator.eagle3
Text Generation • 2B • Updated • 325 • 1 -
RedHatAI/Qwen3-8B-speculator.eagle3
Text Generation • 1B • Updated • 86.8k • 2 -
RedHatAI/Qwen3-14B-speculator.eagle3
Text Generation • 1B • Updated • 610
May 2025 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio.
-
RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic
Image-Text-to-Text • 109B • Updated • 11.9k • 28 -
RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16
Image-Text-to-Text • 20B • Updated • 7.64k • 12 -
RedHatAI/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • 109B • Updated • 10.4k -
RedHatAI/Llama-4-Maverick-17B-128E-Instruct
Image-Text-to-Text • 402B • Updated • 6 • 3
Embedding models act as the bridge between raw, unstructured data and the numerical, vector-based format needed for efficient retrieval in GenAI apps.
IBM and NASA have teamed up to create a family of AI foundation models for Earth called Prithvi.
Collection of quantized Gemma 3 models created by Google.
-
RedHatAI/gemma-3-27b-it-quantized.w4a16
Image-Text-to-Text • 7B • Updated • 58.7k • 13 -
RedHatAI/gemma-3-12b-it-quantized.w4a16
Image-Text-to-Text • 4B • Updated • 13.4k • 3 -
RedHatAI/gemma-3-4b-it-quantized.w4a16
Image-Text-to-Text • 2B • Updated • 1.2k • 5 -
RedHatAI/gemma-3-1b-it-quantized.w8a8
Text Generation • 1B • Updated • 791 • 1
Collection of quantized whisper models created by OpenAI
-
RedHatAI/whisper-large-v3-turbo-quantized.w4a16
Automatic Speech Recognition • 0.2B • Updated • 426 • 7 -
RedHatAI/whisper-large-v3-turbo-quantized.w8a8
Automatic Speech Recognition • 0.9B • Updated • 108 • 4 -
RedHatAI/whisper-large-v3-turbo-FP8-dynamic
Automatic Speech Recognition • 0.9B • Updated • 195 • 6 -
RedHatAI/whisper-tiny-FP8-Dynamic
Automatic Speech Recognition • 57.8M • Updated • 5
Quantized variants of the Llama 4 release by Meta.
-
RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic
Image-Text-to-Text • 109B • Updated • 11.9k • 28 -
RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16
Image-Text-to-Text • 20B • Updated • 7.64k • 12 -
RedHatAI/Llama-4-Maverick-17B-128E-Instruct-FP8
Image-Text-to-Text • 402B • Updated • 17.4k • 2 -
RedHatAI/Llama-4-Maverick-17B-128E-Instruct-quantized.w4a16
Image-Text-to-Text • 59B • Updated • 126 • 1
Collection of quantized Qwen 3 models from Alibaba Cloud.
-
RedHatAI/Qwen3-4B-quantized.w4a16
Text Generation • 1B • Updated • 13.5k • 4 -
RedHatAI/Qwen3-32B-FP8-dynamic
Text Generation • 33B • Updated • 8.11k • 15 -
RedHatAI/Qwen3-0.6B-FP8-dynamic
Text Generation • 0.8B • Updated • 1.55k • 1 -
RedHatAI/Qwen3-8B-FP8-dynamic
Text Generation • 8B • Updated • 19.7k • 12
Quantized variants of Mistral Small 3.1 (2503) Instruct.
-
RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic
Image-Text-to-Text • 24B • Updated • 3.25k • 9 -
RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8
Image-Text-to-Text • 24B • Updated • 305 • 5 -
RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16
Image-Text-to-Text • 5B • Updated • 2.51k • 10
Quantized variants of Phi-4 family of small language and multi-modal models by Microsoft.
Quantized variants of Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out).
Quantized variants of Qwen 2.5 Instruct and Qwen VL models
-
RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w8a8
Image-Text-to-Text • 8B • Updated • 45.7k • 9 -
RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w4a16
Image-Text-to-Text • 3B • Updated • 2.27k • 8 -
RedHatAI/Qwen2.5-7B-quantized.w8a8
Text Generation • 8B • Updated • 5 • 1 -
RedHatAI/Qwen2.5-VL-72B-Instruct-FP8-dynamic
Image-Text-to-Text • 73B • Updated • 1.99k • 15
Quantized Granite models from IBM Research.
-
RedHatAI/granite-3.1-8b-instruct-quantized.w8a8
Text Generation • 8B • Updated • 177 • 2 -
RedHatAI/granite-3.1-2b-base-quantized.w8a8
Text Generation • 3B • Updated • 6 -
RedHatAI/granite-3.1-8b-instruct-quantized.w4a16
Text Generation • 1B • Updated • 789 • 1 -
RedHatAI/granite-3.1-2b-instruct-quantized.w8a8
Text Generation • 3B • Updated • 28
Collection of kernels from vLLM built using https://github.com/huggingface/kernel-builder