NM Testing

company

AI & ML interests

None defined yet.

Recent Activity

HDCharles updated a model about 7 hours ago

nm-testing/Qwen3-4B-mixed-quant-RTN-wNaM-a4

nm-autobot updated a model about 20 hours ago

nm-testing/w4a16_moe-e2e

nm-autobot updated a model about 20 hours ago

nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e

View all activity

nm-testing 's models 559

nm-testing/llava-1.5-7b-hf-FP8-dynamic

7B • Updated Nov 1, 2024 • 3

nm-testing/Llama-3.2-1B-Instruct-HQQ

0.8B • Updated Oct 30, 2024 • 1

nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned_50.2of4-INT8-compressed

0.6B • Updated Oct 29, 2024 • 16

nm-testing/llava-onevision-qwen2-7b-ov-hf-FP8-dynamic

8B • Updated Oct 29, 2024 • 116 • 1

nm-testing/Qwen2-VL-7B-Instruct-FP8-dynamic

8B • Updated Oct 29, 2024 • 110 • 1

nm-testing/Qwen2-VL-7B-Instruct-FP8-dynamic-all

8B • Updated Oct 29, 2024 • 6

nm-testing/paligemma-3b-mix-224-FP8-dynamic

3B • Updated Oct 29, 2024 • 3

nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned_50.2of4-compressed

0.7B • Updated Oct 25, 2024 • 6

nm-testing/Sparse-Llama-3.1-8B-gsm8k-2of4-quantized.w4a16

2B • Updated Oct 24, 2024 • 4

nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-FP8

8B • Updated Oct 24, 2024 • 3

nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-quantized.w8a8

8B • Updated Oct 24, 2024 • 6

nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned_50.2of4-uncompressed

1B • Updated Oct 23, 2024 • 7

nm-testing/SparseLlama-3-8B-pruned_50.2of4_Fp8-compressed

5B • Updated Oct 22, 2024 • 1

nm-testing/Phi-3.5-vision-instruct-W8A8-Dynamic-Per-Token

4B • Updated Oct 17, 2024 • 6

nm-testing/Phi-3.5-vision-instruct-FP8-dynamic

4B • Updated Oct 17, 2024 • 1.31k

nm-testing/MiniCPM-V-2_6-FP8-dynamic

8B • Updated Oct 17, 2024 • 66

nm-testing/tinyllama-one-shot-w4a16-group-packed

Text Generation • 1B • Updated Oct 10, 2024 • 8

nm-testing/llama1.1b_0.5_sparse_bitmask

Text Generation • 0.8B • Updated Oct 9, 2024 • 9

nm-testing/llama7b-one-shot-2_4-w4a16-packed

Text Generation • 1B • Updated Oct 9, 2024 • 4

nm-testing/tinyllama-one-shot-w4a16-group128-packed

Text Generation • 0.3B • Updated Oct 9, 2024 • 4

nm-testing/tinyllama-one-shot-w4a16-channel-packed

Text Generation • 0.3B • Updated Oct 9, 2024 • 5

nm-testing/tinyllama-one-shot-w4a16-channel-compressed

Text Generation • 1B • Updated Oct 9, 2024 • 23

nm-testing/tinyllama-one-shot-dynamic-test

Text Generation • 1B • Updated Oct 9, 2024 • 8

nm-testing/tinyllama-one-shot-static-quant-test-compressed

Text Generation • 1B • Updated Oct 9, 2024 • 14

nm-testing/asym-w8w8-int8-static-per-tensor-tiny-llama

1B • Updated Oct 9, 2024 • 9.45k

nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2-asym

1B • Updated Oct 9, 2024 • 86

nm-testing/OLMoE-1B-7B-0924-Instruct-FP8

7B • Updated Oct 9, 2024 • 242

nm-testing/DeepSeek-Coder-V2-Lite-Instruct-W8A8

16B • Updated Oct 9, 2024 • 8

nm-testing/tinyllama-w8a8-compressed

1B • Updated Oct 9, 2024 • 937

nm-testing/tinyllama-w4a16-compressed

1B • Updated Oct 9, 2024 • 1.43k