nm-testing/DeepSeek-V2-Lite-W8A8-Dynamic-Per-Token
16B • Updated • 3
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4-Updated4
0.7B • Updated • 2
nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4-Updated3
0.7B • Updated • 4
nm-testing/Devstral-Small-2505-FP8-dynamic
Text Generation • 24B • Updated • 41 • 1
nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A8-updated-smoothquant
47B • Updated • 5
nm-testing/Sparse-Llama-3.1-8B-2of4-tldr
Text Generation • 5B • Updated • 3
nm-testing/DeepSeek-Coder-V2-Lite-Instruct-W8A8-smoothquant
16B • Updated • 4
nm-testing/DeepSeek-Coder-V2-Lite-Instruct-W8A8-No-smoothquant
16B • Updated • 7
nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A8-No-Smoothquant
47B • Updated • 5
nm-testing/llama2.c-stories15M-ultrachat-mixed-compressed
14.6M • Updated • 1.61k
nm-testing/llama2.c-stories15M-ultrachat-mixed-uncompressed
24.4M • Updated • 5.43k
nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A8
47B • Updated • 5
nm-testing/TinyLlama-1.1B-Chat-v1.0-FP4
0.7B • Updated • 96 • 1
nm-testing/Llama-3_1-Nemotron-Ultra-253B-v1-FP8-dynamic
253B • Updated • 17 • 2
nm-testing/Mistral-Small-3.1-24B-Instruct-2503-FP8
Image-Text-to-Text • Updated • 9 • 4
nm-testing/DeepSeek-Coder-V2-Lite-Instruct-quantized.w8a8
16B • Updated • 6
nm-testing/l4-scout-int4-debug
20B • Updated • 3
nm-testing/pixtral-12b-FP8-dynamic
Image-Text-to-Text • Updated • 185 • 1
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-Asym-Updated-ActOrder
0.3B • Updated • 11.9k
nm-testing/TinyLlama-1.1B-Chat-v1.0-awq-group128-asym256
0.3B • Updated • 5
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-Asym-Updated-Channel
0.3B • Updated • 4
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-Asym-Updated
0.3B • Updated • 1
nm-testing/Llama-2-7b-hf-gsm8k-quant_w4a16_sym-uncompressed
7B • Updated • 2
nm-testing/Llama-2-7b-hf-gsm8k-quant_w4a16_sym-compressed
1B • Updated • 3
nm-testing/Llama-2-7b-hf-gsm8k-gptq_w4a16_sym-uncompressed
7B • Updated • 2
nm-testing/Llama-2-7b-hf-gsm8k-gptq_w4a16_sym-compressed
1B • Updated • 3
nm-testing/Llama-2-7b-hf-gsm8k-awq_w4a16_sym-uncompressed
7B • Updated • 5
nm-testing/Llama-2-7b-hf-gsm8k-awq_w4a16_sym-compressed
1B • Updated • 2
nm-testing/Llama-2-7b-hf-gsm8k-awq_gptq_sym-uncompressed
7B • Updated • 2
nm-testing/Llama-2-7b-hf-gsm8k-awq_gptq_sym-compressed
1B • Updated • 3