Edit Models filters

Inference status

Misc

compressed-tensors

Inference Endpoints

AutoTrain Compatible

text-generation-inference

8-bit precision

Misc with no match

4-bit precision

text-embeddings-inference

Carbon Emissions

Mixture of Experts

Models

699

Full-text search

Active filters: compressed-tensors

nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token

Text Generation • Updated Oct 9, 2024 • 13

nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token-2048-Samples

Text Generation • Updated Oct 9, 2024 • 5.27k

nm-testing/tinyllama-oneshot-w8a16-per-channel

Text Generation • Updated Oct 9, 2024 • 4.45k

nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test

Text Generation • Updated Oct 9, 2024 • 181

nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test

Text Generation • Updated Oct 9, 2024 • 15

nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test

Text Generation • Updated Oct 9, 2024 • 5.41k

nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos

Text Generation • Updated Oct 9, 2024 • 14

nm-testing/TinyLlama-1.1B-compressed-tensors-kv-cache-scheme

Text Generation • Updated Oct 9, 2024 • 30.4k

nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test

Text Generation • Updated Oct 9, 2024 • 14

nm-testing/Qwen2-0.5B-Instruct

Text Generation • Updated Oct 9, 2024 • 12

neuralmagic/Llama-2-7b-chat-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 577 • 1

neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 1.13k • 2

neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 1.22k

nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise

Text Generation • Updated Oct 9, 2024 • 26

neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 262

neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16

Text Generation • Updated Oct 9, 2024 • 447k • 3

neuralmagic/Qwen2-7B-Instruct-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 520

neuralmagic/Meta-Llama-3-70B-Instruct-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 183

neuralmagic/Qwen2-72B-Instruct-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 148 • 1

nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V

Text Generation • Updated Oct 9, 2024 • 30

nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors

Text Generation • Updated Oct 9, 2024 • 1.05k

nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors

Text Generation • Updated Oct 9, 2024 • 12

nm-testing/nonuniform

Text Generation • Updated Oct 9, 2024 • 12

nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test

Text Generation • Updated Oct 9, 2024 • 1.05k

neuralmagic/Mistral-7B-Instruct-v0.3-quantized.w8a8

Text Generation • Updated Oct 9, 2024 • 299 • 1

nm-testing/Meta-Llama-3-405B-Instruct-Up-Merge-fp8

Text Generation • Updated Oct 9, 2024 • 82 • 4

nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8

Text Generation • Updated Oct 9, 2024 • 7

nm-testing/Meta-llama3-8b-Instruct-quant-FP8

Text Generation • Updated Oct 9, 2024 • 5

nm-testing/Llama-2-70b-chat-hf-W8A8-Dynamic-Per-Token

Text Generation • Updated Oct 9, 2024 • 4

nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test

Text Generation • Updated Oct 9, 2024 • 8