meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 9.55M • • 5.82k
HIGGS-stiched
Stitched HIGGS Llama3 8B mixed-precision model variants.
-
-
RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8-dynamic
Text Generation • 8B • Updated • 65.9k • 9 -
RedHatAI/Llama-3.1-8B-Instruct-NVFP4
Text Generation • 5B • Updated • 18k • 1 -
Qwen/Qwen3-8B
Text Generation • 8B • Updated • 11.5M • • 1.09k -
RedHatAI/Qwen3-8B-FP8-dynamic
Text Generation • 8B • Updated • 34.9k • 12 -
RedHatAI/Qwen3-8B-NVFP4
Text Generation • 5B • Updated • 3.38k • 2 -
inference-optimization/llama3_8b_5.0_bits_mode_heuristic_stiched
5B • Updated • 24 -
inference-optimization/llama3_8b_5.0_bits_mode_hybrid_stiched
5B • Updated • 24 -
inference-optimization/llama3_8b_5.0_bits_mode_noise_stiched
5B • Updated • 21 -
inference-optimization/llama3_8b_5.5_bits_mode_heuristic_stiched
6B • Updated • 20 -
inference-optimization/llama3_8b_5.5_bits_mode_hybrid_stiched
6B • Updated • 26 -
inference-optimization/llama3_8b_5.5_bits_mode_noise_stiched
6B • Updated • 28 -
inference-optimization/llama3_8b_6.0_bits_mode_heuristic_stiched
6B • Updated • 22 -
inference-optimization/llama3_8b_6.0_bits_mode_hybrid_stiched
6B • Updated • 47 -
inference-optimization/llama3_8b_6.0_bits_mode_noise_stiched
6B • Updated • 28 -
inference-optimization/llama3_8b_6.5_bits_mode_heuristic_stiched
7B • Updated • 22 -
inference-optimization/llama3_8b_6.5_bits_mode_hybrid_stiched
7B • Updated • 24 -
inference-optimization/llama3_8b_6.5_bits_mode_noise_stiched
7B • Updated • 25 -
inference-optimization/llama3_8b_7.0_bits_mode_heuristic_stiched
7B • Updated • 24 -
inference-optimization/llama3_8b_7.0_bits_mode_hybrid_stiched
7B • Updated • 28 -
inference-optimization/llama3_8b_7.0_bits_mode_noise_stiched
7B • Updated • 27 -
inference-optimization/qwen3_8b_5.0_bits_mode_heuristic_stiched
6B • Updated • 25 -
inference-optimization/qwen3_8b_5.0_bits_mode_hybrid_stiched
6B • Updated • 28 -
inference-optimization/qwen3_8b_5.0_bits_mode_noise_stiched
6B • Updated • 26 -
inference-optimization/qwen3_8b_5.5_bits_mode_heuristic_stiched
6B • Updated • 26 -
inference-optimization/qwen3_8b_5.5_bits_mode_hybrid_stiched
6B • Updated • 27 -
inference-optimization/qwen3_8b_5.5_bits_mode_noise_stiched
6B • Updated • 23 -
inference-optimization/qwen3_8b_6.0_bits_mode_heuristic_stiched
6B • Updated • 26 -
inference-optimization/qwen3_8b_6.0_bits_mode_hybrid_stiched
6B • Updated • 21 -
inference-optimization/qwen3_8b_6.0_bits_mode_noise_stiched
6B • Updated • 27 -
inference-optimization/qwen3_8b_6.5_bits_mode_heuristic_stiched
7B • Updated • 27 -
inference-optimization/qwen3_8b_6.5_bits_mode_hybrid_stiched
7B • Updated • 24 -
inference-optimization/qwen3_8b_6.5_bits_mode_noise_stiched
7B • Updated • 29 -
inference-optimization/qwen3_8b_7.0_bits_mode_heuristic_stiched
7B • Updated • 27 -
inference-optimization/qwen3_8b_7.0_bits_mode_hybrid_stiched
7B • Updated • 27 -
inference-optimization/qwen3_8b_7.0_bits_mode_noise_stiched
7B • Updated • 27