Image created with Flux Pro v1.1 Ultra. Image prompt: Llama, llama profile silhouette outlined by a tidy chain of small bananas, desert-texture base, photorealistic, editorial, minimal, high detail, 3:2 landscape
For llama.vim the recommended setup now is Qwen 3 Coder 30B A3B Instruct: brew install llama.cpp llama-server –fim-qwen-30b-default Amazingly, on Macs the 30B MoE model performs better than the old Qwen 2.5 Coder 7B so if you have the necessary RAM it’s better to switch to https://x.com/ggerganov/status/1961471397428883882
Hermes 4: Nous Research Open-Weight Reasoning Family Models – 70B / 405B (Llama-3.1 bases, released) – 14B (Qwen3 base, research baseline) Hermes 4 70B & 405B – Base: Llama-3.1-70B / 405B – Training: TorchTitan (modified), Axolotl, 192× B200s, FSDP and TP – Dataset: 56B tokens https://x.com/gm8xx8/status/1962943078702186627
