Custom Models Bunch of bad models soyrsoyr/erebus-487m-instruct 0.5B • Updated Jun 10 • 4 soyrsoyr/erebus-487m-base 0.5B • Updated Apr 15 • 5 soyrsoyr/erebus-v2-1.5b-base Text Generation • 2B • Updated 27 days ago • 64 soyrsoyr/erebus-v2-1.5b-tool Text Generation • 2B • Updated 25 days ago • 48
Quantized Models Bunch of good models Llama-3.2-1B-Instruct GPTQ Quantized Collection GPTQ quantized across W4A16, W8A8, FP8, NVFP4 using llm-compressor. • 4 items • Updated 10 days ago DeepSeek-MoE-16B-Chat GPTQ Quantized Collection DeepSeek-MoE-16B-Chat quantized with GPTQ via llm-compressor: W8A8, W4A16, FP8, NVFP4. • 4 items • Updated 10 days ago Gemma 4 12B Quantized Collection 3 items • Updated 10 days ago soyrsoyr/Qwen3.6-27B-W4A16-AWQ-GPTQ Text Generation • 27B • Updated 25 days ago • 560
Llama-3.2-1B-Instruct GPTQ Quantized Collection GPTQ quantized across W4A16, W8A8, FP8, NVFP4 using llm-compressor. • 4 items • Updated 10 days ago
DeepSeek-MoE-16B-Chat GPTQ Quantized Collection DeepSeek-MoE-16B-Chat quantized with GPTQ via llm-compressor: W8A8, W4A16, FP8, NVFP4. • 4 items • Updated 10 days ago
Custom Models Bunch of bad models soyrsoyr/erebus-487m-instruct 0.5B • Updated Jun 10 • 4 soyrsoyr/erebus-487m-base 0.5B • Updated Apr 15 • 5 soyrsoyr/erebus-v2-1.5b-base Text Generation • 2B • Updated 27 days ago • 64 soyrsoyr/erebus-v2-1.5b-tool Text Generation • 2B • Updated 25 days ago • 48
Quantized Models Bunch of good models Llama-3.2-1B-Instruct GPTQ Quantized Collection GPTQ quantized across W4A16, W8A8, FP8, NVFP4 using llm-compressor. • 4 items • Updated 10 days ago DeepSeek-MoE-16B-Chat GPTQ Quantized Collection DeepSeek-MoE-16B-Chat quantized with GPTQ via llm-compressor: W8A8, W4A16, FP8, NVFP4. • 4 items • Updated 10 days ago Gemma 4 12B Quantized Collection 3 items • Updated 10 days ago soyrsoyr/Qwen3.6-27B-W4A16-AWQ-GPTQ Text Generation • 27B • Updated 25 days ago • 560
Llama-3.2-1B-Instruct GPTQ Quantized Collection GPTQ quantized across W4A16, W8A8, FP8, NVFP4 using llm-compressor. • 4 items • Updated 10 days ago
DeepSeek-MoE-16B-Chat GPTQ Quantized Collection DeepSeek-MoE-16B-Chat quantized with GPTQ via llm-compressor: W8A8, W4A16, FP8, NVFP4. • 4 items • Updated 10 days ago