I tried another model, the 'llama-translate" found here; https://huggingface.co/dahara1/llama-translate-gguf
It actually seems to handle singular words and paragraphs just fine. However, it is pretty excruciatingly slow on my PC, but then again I only have a 980 ti. Give it a try with this JSON body:
{
"prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\nYou are a highly skilled professional translator.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n### Instruction:\nTranslate %source% to %target%.\n\n### Input:\\n%text%。\n\n### Response\n<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n",
"max_new_tokens": 256,
"temperature": 0,
"top_p": 1,
"do_sample": false
}