Collection on FP8 Quantization of Weights, Activations and KV Cache
NM Testing
company
AI & ML interests
None defined yet.
-
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors
Text Generation • 8B • Updated • 21 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 1 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 7.78k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 4 • 1
Collection on FP8 Quantization of Weights, Activations and KV Cache
-
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors
Text Generation • 8B • Updated • 21 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 1 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 7.78k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 4 • 1
models 477
nm-testing/tinyllama-w8a16-dense
1B • Updated
• 743
nm-testing/Meta-Llama-3-8B-Instruct-MXFP4A16
5B • Updated
• 5
nm-testing/Qwen3-30B-A3B-MXFP4A16
17B • Updated
• 5.14k
nm-testing/Meta-Llama-3-8B-Instruct-awq-asym-fp8-dynamic
8B • Updated
• 11
nm-testing/Meta-Llama-3-8B-Instruct-awq-asym-fp8-block
8B • Updated
• 8
nm-testing/DeepSeek-V2-Lite-FP8-BLOCK-Fused
16B • Updated
• 9
nm-testing/woah
0.6B • Updated
• 7
nm-testing/tinysmokeqwen3
2.64M • Updated
• 5.05k
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4A16-GPTQ
5B • Updated
nm-testing/Meta-Llama-3-8B-Instruct-NVFP4-GPTQ-ActOrder
5B • Updated
datasets 6
nm-testing/ultrachat_gpt_oss_20b_hidden_states
Updated
• 15
nm-testing/sharegpt_qwen3_8b_hidden_states
Updated
• 10
nm-testing/ultrachat_qwen3_8b_hidden_states
Updated
• 11
nm-testing/sharegpt_llama3_8b_token_freq
Updated
• 15
nm-testing/sharegpt_llama3_8b_hidden_states
Viewer
• Updated
• 1 • 244
nm-testing/qa-chat-prompts
Viewer
• Updated
• 200 • 21 • 2