What GPU do you need to run PLaMo 3 Translate 2B?

2.88B parameters (Hugging Face, accessed 2026-11-10). Q4_K_M GGUF: 1.81 GB (source). Architecture config (Hugging Face config.json; 24 layers, window_size 2048, sliding_window_pattern 8: llama.cpp plamo3 (load_swa_pattern(ml, 8), LLAMA_SWA_TYPE_STANDARD) makes layer il sliding-window unless il % 8 == 7, so 3 full-attention + 21 sliding-window layers; the official GGUF metadata says the same (sliding_window 2048, sliding_window_pattern 8). max_ctx is the model card's 32,768-token training limit for input and output combined (the context field), not config.json's max_position_embeddings 262,144): 3 global attention layers × 4 KV heads × 128 head dim, plus 21 sliding-window layers (2048-token window), so about 6 KB of FP16 KV cache per token of context (how we estimate context).

Translation model, not a general chat assistant: it takes text in one language and returns a translation, through its own translation prompt format. Dense model, one of four PLaMo 3 Translate sizes. Context is 32,768 tokens because the model card says training used at most 32,768 tokens of input and output combined and asks you to split anything longer; config.json allows 262,144 positions, which this page does not treat as usable. Commercial use needs advance registration with Preferred Networks (see License below). Release date is the date of PFN's release blog post.