models.txt

gptq_marlin, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
gptq_marlin, TheBloke/Llama-2-7B-GPTQ, main
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, main
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit-32g-actorder_True
gptq_marlin, TechxGenus/gemma-1.1-2b-it-GPTQ, main
gptq, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
gptq, TheBloke/Llama-2-7B-GPTQ, main
gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, main
gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit-32g-actorder_True
gptq, TechxGenus/gemma-1.1-2b-it-GPTQ, main
compressed-tensors, nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change, main
compressed-tensors, nm-testing/tinyllama-oneshot-w8-channel-a8-tensor, main
compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2, main
compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2, main
compressed-tensors, nm-testing/tinyllama-oneshot-w4a16-group128-v2, main
compressed-tensors, nm-testing/tinyllama-oneshot-w8a16-per-channel, main
compressed-tensors, nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test, main
compressed-tensors, nm-testing/Phi-3-mini-128k-instruct-FP8, main
compressed-tensors, neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16, main
compressed-tensors, nm-testing/TinyLlama-1.1B-Chat-v1.0-actorder-group, main
#compressed-tensors, mgoin/DeepSeek-Coder-V2-Lite-Instruct-FP8, main
compressed-tensors, nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-FP8-Dynamic-testing, main, 90
compressed-tensors, nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-W8A8-testing, main, 90
awq, casperhansen/mixtral-instruct-awq, main
awq_marlin, casperhansen/mixtral-instruct-awq, main
fp8, neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV, main
None, mgleize/fairseq2-dummy-Llama-3.2-1B, main