Nemotron nvidia/Llama-3_3-Nemotron-Super-49B-v1 Text Generation • 50B • Updated Oct 15, 2025 • 189k • 324 nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 Text Generation • 5B • Updated Oct 15, 2025 • 3.08k • 115 TheDrummer/Valkyrie-49B-v1 50B • Updated May 25, 2025 • 13 • 58
Best for RP on mobile dGPU Models without twee romantic language, absurd bad erotica cliches or low coherence. These models are top of their weight class. RichardErkhov/shadowml_-_DareBeagel-2x7B-gguf Updated Aug 31, 2024 • 88 mradermacher/IceLemonTeaRP-32k-7b-GGUF 7B • Updated May 6, 2024 • 23 • 12 bartowski/L3-8B-Lunaris-v1-GGUF Text Generation • Updated Jun 29, 2024 • 3.19k • 26
Nemotron nvidia/Llama-3_3-Nemotron-Super-49B-v1 Text Generation • 50B • Updated Oct 15, 2025 • 189k • 324 nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 Text Generation • 5B • Updated Oct 15, 2025 • 3.08k • 115 TheDrummer/Valkyrie-49B-v1 50B • Updated May 25, 2025 • 13 • 58
Best for RP on mobile dGPU Models without twee romantic language, absurd bad erotica cliches or low coherence. These models are top of their weight class. RichardErkhov/shadowml_-_DareBeagel-2x7B-gguf Updated Aug 31, 2024 • 88 mradermacher/IceLemonTeaRP-32k-7b-GGUF 7B • Updated May 6, 2024 • 23 • 12 bartowski/L3-8B-Lunaris-v1-GGUF Text Generation • Updated Jun 29, 2024 • 3.19k • 26