meta-llama/Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 7.63M • • 1.4k
HIGGS-per-tensor
-
-
inference-optimization/Llama-3.2-1B-Instruct-FP8-Dynamic
1B • Updated • 29 -
inference-optimization/Llama-3.2-1B-Instruct-NVFP4
0.8B • Updated • 33 -
inference-optimization/Llama-3.2-1B-Instruct-5-bits-mode-heuristic-per-tensor
1B • Updated • 35 -
inference-optimization/Llama-3.2-1B-Instruct-5-bits-mode-hybrid-per-tensor
1B • Updated • 39 -
inference-optimization/Llama-3.2-1B-Instruct-5-bits-mode-noise-per-tensor
1B • Updated • 36 -
inference-optimization/Llama-3.2-1B-Instruct-5.5-bits-mode-heuristic-per-tensor
1B • Updated • 38 -
inference-optimization/Llama-3.2-1B-Instruct-5.5-bits-mode-hybrid-per-tensor
1B • Updated • 36 -
inference-optimization/Llama-3.2-1B-Instruct-5.5-bits-mode-noise-per-tensor
1B • Updated • 36 -
inference-optimization/Llama-3.2-1B-Instruct-6-bits-mode-heuristic-per-tensor
1B • Updated • 36 -
inference-optimization/Llama-3.2-1B-Instruct-6-bits-mode-hybrid-per-tensor
1B • Updated • 35 -
inference-optimization/Llama-3.2-1B-Instruct-6-bits-mode-noise-per-tensor
1B • Updated • 41 -
inference-optimization/Llama-3.2-1B-Instruct-6.5-bits-mode-heuristic-per-tensor
1B • Updated • 36 -
inference-optimization/Llama-3.2-1B-Instruct-6.5-bits-mode-hybrid-per-tensor
1B • Updated • 36 -
inference-optimization/Llama-3.2-1B-Instruct-6.5-bits-mode-noise-per-tensor
1B • Updated • 35 -
inference-optimization/Llama-3.2-1B-Instruct-7-bits-mode-heuristic-per-tensor
1B • Updated • 35 -
inference-optimization/Llama-3.2-1B-Instruct-7-bits-mode-hybrid-per-tensor
1B • Updated • 37 -
inference-optimization/Llama-3.2-1B-Instruct-7-bits-mode-noise-per-tensor
1B • Updated • 36 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 2.43M • • 2.13k -
inference-optimization/Llama-3.2-3B-Instruct-FP8-Dynamic
3B • Updated • 27 -
inference-optimization/Llama-3.2-3B-Instruct-NVFP4
2B • Updated • 292 -
inference-optimization/Llama-3.2-3B-Instruct-5-bits-mode-heuristic-per-tensor
3B • Updated • 33 -
inference-optimization/Llama-3.2-3B-Instruct-5-bits-mode-hybrid-per-tensor
3B • Updated • 35 -
inference-optimization/Llama-3.2-3B-Instruct-5-bits-mode-noise-per-tensor
3B • Updated • 35 -
inference-optimization/Llama-3.2-3B-Instruct-5.5-bits-mode-heuristic-per-tensor
3B • Updated • 36 -
inference-optimization/Llama-3.2-3B-Instruct-5.5-bits-mode-hybrid-per-tensor
3B • Updated • 35 -
inference-optimization/Llama-3.2-3B-Instruct-5.5-bits-mode-noise-per-tensor
3B • Updated • 39 -
inference-optimization/Llama-3.2-3B-Instruct-6-bits-mode-heuristic-per-tensor
3B • Updated • 67 -
inference-optimization/Llama-3.2-3B-Instruct-6-bits-mode-hybrid-per-tensor
3B • Updated • 47 -
inference-optimization/Llama-3.2-3B-Instruct-6-bits-mode-noise-per-tensor
3B • Updated • 40 -
inference-optimization/Llama-3.2-3B-Instruct-6.5-bits-mode-heuristic-per-tensor
3B • Updated • 35 -
inference-optimization/Llama-3.2-3B-Instruct-6.5-bits-mode-hybrid-per-tensor
3B • Updated • 39 -
inference-optimization/Llama-3.2-3B-Instruct-6.5-bits-mode-noise-per-tensor
3B • Updated • 34 -
inference-optimization/Llama-3.2-3B-Instruct-7-bits-mode-heuristic-per-tensor
3B • Updated • 39 -
inference-optimization/Llama-3.2-3B-Instruct-7-bits-mode-hybrid-per-tensor
3B • Updated • 34 -
inference-optimization/Llama-3.2-3B-Instruct-7-bits-mode-noise-per-tensor
3B • Updated • 37 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 10M • • 5.84k -
RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8-dynamic
Text Generation • 8B • Updated • 65.3k • 9 -
RedHatAI/Llama-3.1-8B-Instruct-NVFP4
Text Generation • 5B • Updated • 17.1k • 1 -
inference-optimization/Llama-3.1-8B-Instruct-5-bits-mode-heuristic-per-tensor
5B • Updated • 57 -
inference-optimization/Llama-3.1-8B-Instruct-5-bits-mode-hybrid-per-tensor
5B • Updated • 52 -
inference-optimization/Llama-3.1-8B-Instruct-5-bits-mode-noise-per-tensor
5B • Updated • 46 -
inference-optimization/Llama-3.1-8B-Instruct-5.5-bits-mode-heuristic-per-tensor
6B • Updated • 53 -
inference-optimization/Llama-3.1-8B-Instruct-5.5-bits-mode-hybrid-per-tensor
6B • Updated • 59 -
inference-optimization/Llama-3.1-8B-Instruct-5.5-bits-mode-noise-per-tensor
6B • Updated • 52 -
inference-optimization/Llama-3.1-8B-Instruct-6-bits-mode-heuristic-per-tensor
6B • Updated • 70 -
inference-optimization/Llama-3.1-8B-Instruct-6-bits-mode-hybrid-per-tensor
6B • Updated • 64 -
inference-optimization/Llama-3.1-8B-Instruct-6-bits-mode-noise-per-tensor
6B • Updated • 62 -
inference-optimization/Llama-3.1-8B-Instruct-6.5-bits-mode-heuristic-per-tensor
7B • Updated • 55 -
inference-optimization/Llama-3.1-8B-Instruct-6.5-bits-mode-hybrid-per-tensor
7B • Updated • 66 -
inference-optimization/Llama-3.1-8B-Instruct-6.5-bits-mode-noise-per-tensor
7B • Updated • 51 -
inference-optimization/Llama-3.1-8B-Instruct-7-bits-mode-heuristic-per-tensor
7B • Updated • 58 -
inference-optimization/Llama-3.1-8B-Instruct-7-bits-mode-hybrid-per-tensor
7B • Updated • 52 -
inference-optimization/Llama-3.1-8B-Instruct-7-bits-mode-noise-per-tensor
7B • Updated • 55 -
Qwen/Qwen3-8B
Text Generation • 8B • Updated • 11.6M • • 1.09k -
RedHatAI/Qwen3-8B-FP8-dynamic
Text Generation • 8B • Updated • 41.8k • 12 -
RedHatAI/Qwen3-8B-NVFP4
Text Generation • 5B • Updated • 3.27k • 2 -
inference-optimization/Qwen3-8B-5-bits-mode-heuristic-per-tensor
6B • Updated • 67 -
inference-optimization/Qwen3-8B-5-bits-mode-hybrid-per-tensor
6B • Updated • 71 -
inference-optimization/Qwen3-8B-5-bits-mode-noise-per-tensor
6B • Updated • 64 -
inference-optimization/Qwen3-8B-5.5-bits-mode-heuristic-per-tensor
6B • Updated • 68 -
inference-optimization/Qwen3-8B-5.5-bits-mode-hybrid-per-tensor
6B • Updated • 66 -
inference-optimization/Qwen3-8B-5.5-bits-mode-noise-per-tensor
6B • Updated • 66 -
inference-optimization/Qwen3-8B-6-bits-mode-heuristic-per-tensor
6B • Updated • 68 -
inference-optimization/Qwen3-8B-6-bits-mode-hybrid-per-tensor
6B • Updated • 64 -
inference-optimization/Qwen3-8B-6-bits-mode-noise-per-tensor
6B • Updated • 65 -
inference-optimization/Qwen3-8B-6.5-bits-mode-heuristic-per-tensor
7B • Updated • 74 -
inference-optimization/Qwen3-8B-6.5-bits-mode-hybrid-per-tensor
7B • Updated • 63 -
inference-optimization/Qwen3-8B-6.5-bits-mode-noise-per-tensor
6B • Updated • 68 -
inference-optimization/Qwen3-8B-7-bits-mode-heuristic-per-tensor
7B • Updated • 94 -
inference-optimization/Qwen3-8B-7-bits-mode-hybrid-per-tensor
7B • Updated • 88 -
inference-optimization/Qwen3-8B-7-bits-mode-noise-per-tensor
6B • Updated • 77 -
Qwen/Qwen3-30B-A3B
Text Generation • Updated • 1.68M • • 886 -
RedHatAI/Qwen3-30B-A3B-FP8-dynamic
Text Generation • 31B • Updated • 3.98k • 3 -
RedHatAI/Qwen3-30B-A3B-NVFP4
Text Generation • 17B • Updated • 28.8k • 2 -
inference-optimization/Qwen3-30B-A3B-5-bits-mode-heuristic-per-tensor
19B • Updated • 63 -
inference-optimization/Qwen3-30B-A3B-5-bits-mode-hybrid-per-tensor
19B • Updated • 49 -
inference-optimization/Qwen3-30B-A3B-5-bits-mode-noise-per-tensor
19B • Updated • 47 -
inference-optimization/Qwen3-30B-A3B-5.5-bits-mode-heuristic-per-tensor
21B • Updated • 43 -
inference-optimization/Qwen3-30B-A3B-5.5-bits-mode-hybrid-per-tensor
21B • Updated • 47 -
inference-optimization/Qwen3-30B-A3B-5.5-bits-mode-noise-per-tensor
21B • Updated • 49 -
inference-optimization/Qwen3-30B-A3B-6-bits-mode-heuristic-per-tensor
23B • Updated • 68 -
inference-optimization/Qwen3-30B-A3B-6-bits-mode-hybrid-per-tensor
23B • Updated • 54 -
inference-optimization/Qwen3-30B-A3B-6-bits-mode-noise-per-tensor
23B • Updated • 46 -
inference-optimization/Qwen3-30B-A3B-6.5-bits-mode-heuristic-per-tensor
25B • Updated • 51 -
inference-optimization/Qwen3-30B-A3B-6.5-bits-mode-hybrid-per-tensor
25B • Updated • 48 -
inference-optimization/Qwen3-30B-A3B-6.5-bits-mode-noise-per-tensor
25B • Updated • 51 -
inference-optimization/Qwen3-30B-A3B-7-bits-mode-heuristic-per-tensor
27B • Updated • 63 -
inference-optimization/Qwen3-30B-A3B-7-bits-mode-hybrid-per-tensor
27B • Updated • 54 -
inference-optimization/Qwen3-30B-A3B-7-bits-mode-noise-per-tensor
27B • Updated • 46 -
Qwen/Qwen3-30B-A3B-Instruct-2507
Text Generation • Updated • 1.23M • • 809 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-FP8-Dynamic
31B • Updated • 48 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-NVFP4
17B • Updated • 47 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-5-bits-mode-heuristic-per-tensor
19B • Updated • 55 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-5-bits-mode-hybrid-per-tensor
19B • Updated • 44 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-5-bits-mode-noise-per-tensor
19B • Updated • 46 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-5.5-bits-mode-heuristic-per-tensor
21B • Updated • 48 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-5.5-bits-mode-hybrid-per-tensor
21B • Updated • 44 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-5.5-bits-mode-noise-per-tensor
21B • Updated • 48 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-6-bits-mode-heuristic-per-tensor
23B • Updated • 42 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-6-bits-mode-hybrid-per-tensor
23B • Updated • 46 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-6-bits-mode-noise-per-tensor
23B • Updated • 44 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-6.5-bits-mode-heuristic-per-tensor
25B • Updated • 47 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-6.5-bits-mode-hybrid-per-tensor
25B • Updated • 43 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-6.5-bits-mode-noise-per-tensor
25B • Updated • 44 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-7-bits-mode-heuristic-per-tensor
27B • Updated • 43 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-7-bits-mode-hybrid-per-tensor
27B • Updated • 42 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-7-bits-mode-noise-per-tensor
26B • Updated • 44