nm-testing/Eagle_Speculator_Llama_3_1_8B_TTT_speculators_conversion_test
nm-testing/DeepSeek-Coder-V2-Lite-Instruct-FP8-dynamic
16B
•
Updated
•
4
nm-testing/Llama-3.1-8B-Instruct-NVFP4
5B
•
Updated
•
5
nm-testing/Qwen2.5-VL-7B-Instruct-W4A16_actorder_weight-lm-eval-test
3B
•
Updated
•
6
nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4
0.7B
•
Updated
•
2.43k
nm-testing/Sparse-Llama-3.1-8B-tldr-2of4-quantized.w4a16
2B
•
Updated
•
4
nm-testing/Sparse-Llama-3.1-8B-tldr-2of4-quantized.w8a8
5B
•
Updated
•
3
nm-testing/Meta-Llama-3-8B-Instruct2of4-W8A8-FP8-Dynamic-Per-Token
5B
•
Updated
•
5
nm-testing/Llama-3.3-70B-Instruct-NVFP4-0604-v2
41B
•
Updated
•
6
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-0604
5B
•
Updated
•
8
nm-testing/Qwen3-30B-A3B-Fp8-v1
31B
•
Updated
•
7
nm-testing/Qwen3-30B-A3B-Fp8
31B
•
Updated
•
6
nm-testing/Llama-2-7b-hf-weight-input-quant-compressed
24.4M
•
Updated
•
5
nm-testing/Llama-2-7b-hf-weight-input-quant-uncompressed
24.4M
•
Updated
•
5
nm-testing/Qwen3-30B-A3B-awq-w4a16-g128-sym
5B
•
Updated
•
7
•
1
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-0602-v2
5B
•
Updated
•
8
nm-testing/Llama-3.1-8B-Instruct-NVFP4A16-0602
5B
•
Updated
•
6
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-0602
5B
•
Updated
•
11
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-0531-v3
5B
•
Updated
•
11
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4himBHs0531-v3
5B
•
Updated
•
6
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-0531-v2
5B
•
Updated
•
8
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-0531
5B
•
Updated
•
5
nm-testing/gemma-3-4b-it-quantized.w8a8_previous
29B
•
Updated
•
2
nm-testing/gemma-3-4b-it-quantized.w8a8_temp
5B
•
Updated
•
4
nm-testing/Mistral-Small-3.1-24B-Instruct-2503-W4A16-G128
4B
•
Updated
•
5
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-updated-v2
5B
•
Updated
•
4
nm-testing/Llama-3.1-8B-Instruct-NVFP4A16-temp2
5B
•
Updated
•
3
nm-testing/Llama-3.1-8B-Instruct-NVFP4-v4-temp
5B
•
Updated
•
4
nm-testing/Llama-3.1-8B-Instruct-NVFP4A16-temp
5B
•
Updated
•
5
nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4-v5
0.7B
•
Updated
•
6