Organization
Red Hat AI
Members of RedHatAI on Hugging Face can sign in and add it to their profile.
People 0
LocalMaxxing accounts that Hugging Face lists as members of RedHatAI.No one has added this organization yet.
Models 44
Models under RedHatAI/ on LocalMaxxing, most tested first.- Qwen3.8-27B-INT4RedHatAI/Qwen3.8-27B-INT4
- Speed tests
- 94
- Matrix runs
- 10
- Qwen3.5-4B-FP8-dynamicRedHatAI/Qwen3.5-4B-FP8-dynamic
- Speed tests
- 16
- Matrix runs
- 8
- Qwen3.5-9B-FP8-dynamicRedHatAI/Qwen3.5-9B-FP8-dynamic
- Speed tests
- 16
- Matrix runs
- 7
- NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16RedHatAI/NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16
- Speed tests
- 14
- Matrix runs
- 7
- gemma-4-26B-A4B-it-NVFP4RedHatAI/gemma-4-26B-A4B-it-NVFP4
- Speed tests
- 10
- Matrix runs
- 7
- Llama-3.2-3B-Instruct-FP8-dynamicRedHatAI/Llama-3.2-3B-Instruct-FP8-dynamic
- Speed tests
- 10
- Matrix runs
- 5
- gemma-4-26B-A4B-it-FP8-dynamicRedHatAI/gemma-4-26B-A4B-it-FP8-dynamic
- Speed tests
- 10
- Matrix runs
- 3
- gemma-3-12b-it-FP8-dynamicRedHatAI/gemma-3-12b-it-FP8-dynamic
- Speed tests
- 8
- Matrix runs
- 4
- gemma-4-12B-it-FP8-DynamicRedHatAI/gemma-4-12B-it-FP8-Dynamic
- Speed tests
- 6
- Matrix runs
- 4
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8
- Speed tests
- 9
- Matrix runs
- 1
- Qwen3.5-4B-quantized.w4a16RedHatAI/Qwen3.5-4B-quantized.w4a16
- Speed tests
- 10
- Matrix runs
- 0
- NVIDIA-Nemotron-Nano-9B-v2-FP8-dynamicRedHatAI/NVIDIA-Nemotron-Nano-9B-v2-FP8-dynamic
- Speed tests
- 6
- Matrix runs
- 3
- Muse-Glimmer-30B-FP8-blockRedHatAI/Muse-Glimmer-30B-FP8-block
- Speed tests
- 3
- Matrix runs
- 5
- Qwen3.6-35B-A3B-NVFP4RedHatAI/Qwen3.6-35B-A3B-NVFP4
- Speed tests
- 5
- Matrix runs
- 2
- DeepSeek-R1-Distill-Qwen-14B-FP8-dynamicRedHatAI/DeepSeek-R1-Distill-Qwen-14B-FP8-dynamic
- Speed tests
- 4
- Matrix runs
- 2
- DeepSeek-R1-Distill-Qwen-32B-FP8-dynamicRedHatAI/DeepSeek-R1-Distill-Qwen-32B-FP8-dynamic
- Speed tests
- 4
- Matrix runs
- 2
- Llama-4-Scout-17B-16E-Instruct-quantized.w4a16RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16
- Speed tests
- 5
- Matrix runs
- 0
- gemma-4-31B-it-FP8-dynamicRedHatAI/gemma-4-31B-it-FP8-dynamic
- Speed tests
- 2
- Matrix runs
- 2
- gemma-4-12B-itRedHatAI/gemma-4-12B-it
- Speed tests
- 0
- Matrix runs
- 3
- gemma-4-26B-A4B-itRedHatAI/gemma-4-26B-A4B-it
- Speed tests
- 0
- Matrix runs
- 3
- gemma-4-E2B-itRedHatAI/gemma-4-E2B-it
- Speed tests
- 0
- Matrix runs
- 3
- gemma-4-E4B-itRedHatAI/gemma-4-E4B-it
- Speed tests
- 0
- Matrix runs
- 3
- Llama-3.3-70B-Instruct-FP8-dynamicRedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic
- Speed tests
- 2
- Matrix runs
- 1
- Qwen3.5-9B-quantized.w4a16RedHatAI/Qwen3.5-9B-quantized.w4a16
- Speed tests
- 3
- Matrix runs
- 0
- Qwen3.6-35B-A3B-FP8RedHatAI/Qwen3.6-35B-A3B-FP8
- Speed tests
- 0
- Matrix runs
- 3
- Qwen3.6-35B-A3B-FP8-dynamicRedHatAI/Qwen3.6-35B-A3B-FP8-dynamic
- Speed tests
- 0
- Matrix runs
- 3
- diffusiongemma-26B-A4B-it-FP8-dynamicRedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic
- Speed tests
- 2
- Matrix runs
- 0
- gemma-4-31B-it-FP8-blockRedHatAI/gemma-4-31B-it-FP8-block
- Speed tests
- 0
- Matrix runs
- 2
- gemma-4-31B-it-NVFP4RedHatAI/gemma-4-31B-it-NVFP4
- Speed tests
- 0
- Matrix runs
- 2
- GLM-5.3-Flash-NVFP4RedHatAI/GLM-5.3-Flash-NVFP4
- Speed tests
- 1
- Matrix runs
- 1
- Muse-Glimmer-30BRedHatAI/Muse-Glimmer-30B
- Speed tests
- 0
- Matrix runs
- 2
- Muse-Glimmer-30B-INT4RedHatAI/Muse-Glimmer-30B-INT4
- Speed tests
- 0
- Matrix runs
- 2
- Muse-Glimmer-30B-NVFP4RedHatAI/Muse-Glimmer-30B-NVFP4
- Speed tests
- 0
- Matrix runs
- 2
- Qwen3.6-27B-FP8RedHatAI/Qwen3.6-27B-FP8
- Speed tests
- 0
- Matrix runs
- 2
- Qwen3.6-35B-A3BRedHatAI/Qwen3.6-35B-A3B
- Speed tests
- 0
- Matrix runs
- 2
- Qwen3.8-27B-NVFP4RedHatAI/Qwen3.8-27B-NVFP4
- Speed tests
- 0
- Matrix runs
- 2
- DeepSeek-Coder-V2-Lite-Instruct-FP8RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8
- Speed tests
- 1
- Matrix runs
- 0
- gemma-3n-E4B-it-FP8-dynamicRedHatAI/gemma-3n-E4B-it-FP8-dynamic
- Speed tests
- 0
- Matrix runs
- 1
- gemma-4-12B-it-NVFP4RedHatAI/gemma-4-12B-it-NVFP4
- Speed tests
- 0
- Matrix runs
- 1
- gemma-4-31B-itRedHatAI/gemma-4-31B-it
- Speed tests
- 0
- Matrix runs
- 1
- GLM-5.3-FlashRedHatAI/GLM-5.3-Flash
- Speed tests
- 0
- Matrix runs
- 1
- GLM-5.3-Flash-BF16RedHatAI/GLM-5.3-Flash-BF16
- Speed tests
- 0
- Matrix runs
- 1
- GLM-5.3-MXFP4RedHatAI/GLM-5.3-MXFP4
- Speed tests
- 0
- Matrix runs
- 1
- Qwen3.5-122B-A10B-NVFP4RedHatAI/Qwen3.5-122B-A10B-NVFP4
- Speed tests
- 1
- Matrix runs
- 0