models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
tinyllama-oneshot-w4a16-channel-v2Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Testtinyllama-oneshot-w8a8-channel-dynamic-token-v2zephyr-7b-beta-channelwise-gptqtinyllama-oneshot-w8-channel-a8-tensortinyllama-oneshot-w8a16-per-channelint8_channel_weight_static_per_tensor_act-e2efp8_weight_only_channel-e2ecellfinder_single_channel_defaultQwen2.5-Channel-Coder-14B-Instruct-i1-GGUFQwen2.5-Channel-Coder-14B-Instruct-GGUFDeepSeek-R1-Distill-Llama-8B_s0.50_channelDeepSeek-R1-Channel-INT8zephyr-7b-beta-channelwise-marlintinyllama-oneshot-w8a8-channel-dynamic-token-v2-asymtheworld-spatial-channel-justprojection-fixed-mlpllama3-8b-w8_channel-a8_tensor-compressedDeepSeek-V3.1-Terminus-Channel-int8Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-TestQwen3-30B-A3B-W8A8KV16-FP-WS-CHANNEL-AS-TOKEN-dynamictheworld-spatial-channel-lmandprojection-fixed-mlptinyllama-24-gptq-8bit-channelwiseresnet-50-int8-per-channel-ethos-u-executorchLlama-3.1-8B-Instruct-W8A8KV16-WS-CHANNEL-AS-TOKEN-Wsym-Asym-SpQ-R1R2R4-SmQ-0.5deepseek-ai.DeepSeek-V3.2-Speciale-Channel-INT8theworld-spatial-channel-2CQ3-Qwen3-32B-K4-Channel-FP4Mix-NoSubea-decoder-channel-xgboostCQ3-Qwen3-4B-K4-Channel-FP4Mix-WithSubDeepSeek-R1-0528-Channel-INT8