HomeAI modelsAI modelsShowing 1–32 of 32 AI modelsAI modelsAI modelsModelPublisherParametersQuantizationMin VRAMDeepSeek-R1-Distill-Llama-70B (Q4_K_M)DeepSeek70.6Bq4_k_m42.5 GBDeepSeek-R1-Distill-Llama-8B (Q4_K_M)DeepSeek8Bq4_k_m4.9 GBDeepSeek-R1-Distill-Qwen-14B (Q4_K_M)DeepSeek14.8Bq4_k_m9 GBDeepSeek-R1-Distill-Qwen-32B (Q4_K_M)DeepSeek32.8Bq4_k_m19.9 GBDeepSeek-R1-Distill-Qwen-7B (Q4_K_M)DeepSeek7.6Bq4_k_m4.7 GBGemma 3 12B IT (Q4_K_M)Google12.2Bq4_k_m7.3 GBGemma 3 27B IT (Q4_K_M)Google27.4Bq4_k_m16.6 GBGemma 3 4B IT (Q4_K_M)Google4.3Bq4_k_m2.5 GBgpt-oss-120b (MXFP4)OpenAI116.8Bmxfp463.4 GBgpt-oss-20b (MXFP4)OpenAI20.9Bmxfp412.1 GBLlama 3.1 70B Instruct (Q4_K_M)Meta70.6Bq4_k_m42.5 GBLlama 3.1 8B Instruct (Q4_K_M)Meta8Bq4_k_m4.9 GBLlama 3.2 1B Instruct (Q4_K_M)Meta1.2Bq4_k_m0.8 GBLlama 3.2 3B Instruct (Q4_K_M)Meta3.2Bq4_k_m2 GBLlama 3.3 70B Instruct (Q4_K_M)Meta70.6Bq4_k_m42.5 GBMistral 7B Instruct v0.3 (Q4_K_M)Mistral AI7.3Bq4_k_m4.4 GBMistral Nemo Instruct 2407 (Q4_K_M)Mistral AI12.3Bq4_k_m7.5 GBMistral Small 3.1 24B Instruct 2503 (Q4_K_M)Mistral AI24Bq4_k_m14.3 GBMixtral 8x7B Instruct v0.1 (Q4_K_M)Mistral AI46.7Bq4_k_m26.5 GBPhi-4-mini-instruct (Q4_K_M)Microsoft3.8Bq4_k_m2.5 GBPhi-4 (Q4_K_M)Microsoft14.7Bq4_k_m9.1 GBQwen2.5 14B Instruct (Q4_K_M)Alibaba14.8Bq4_k_m9 GBQwen2.5 32B Instruct (Q4_K_M)Alibaba32.8Bq4_k_m19.9 GBQwen2.5 72B Instruct (Q4_K_M)Alibaba72.7Bq4_k_m44 GBQwen2.5 7B Instruct (Q4_K_M)Alibaba7.6Bq4_k_m4.7 GBQwen2.5-Coder 32B Instruct (Q4_K_M)Alibaba32.8Bq4_k_m19.9 GBQwen3 14B (Q4_K_M)Alibaba14.8Bq4_k_m9 GBQwen3 235B-A22B (Q4_K_M)Alibaba235.1Bq4_k_m142.2 GBQwen3 30B-A3B (Q4_K_M)Alibaba30.5Bq4_k_m18.6 GBQwen3 32B (Q4_K_M)Alibaba32.8Bq4_k_m19.8 GBQwen3 4B (Q4_K_M)Alibaba4Bq4_k_m2.5 GBQwen3 8B (Q4_K_M)Alibaba8.2Bq4_k_m5 GBShowing 1–32 of 32 AI models
