Sugoi LLM 14B Ultra - Download links
Added 2025-07-26 15:27:40 +0000 UTCThe magic of the original FP16 14B model is now fully unleashed in Sugoi 14B Ultra! I have pushed the limits to retain almost every ounce of quality from the source model – and the result? Translation performance that’s ALMOST TWICE as good as the previous quantized Sugoi 14B version! (BLEU score of 21.38 vs 13.67)
But that’s not all – Sugoi 14B Ultra isn’t just accurate, it’s smart. With prompt-following skills rivaling the Qwen 2.5 base model, it’s ready to translate even text with lots of brackets (commonly seen in RPGM games) with unmatched precision.
Instructions:
https://blog.sugoitoolkit.com/sugoi-llm-14b-ultra/
Download links:
https://sugoi-file.sfo3.cdn.digitaloceanspaces.com/Sugoi-14B-Ultra-Q4_K_M.gguf
Comments
if there are more demands from users, I'll consider it because requests like you are right now less than 3 :)
Nguyen Le Minh
2025-08-19 06:42:23 +0000 UTCAre we able to get the non-quantized version? GGUF does not play nicely with certain hosts (particularly vLLM, which is blazing fast)
Pilaxiv724
2025-08-18 21:23:07 +0000 UTCCan you post this on Sugoi Toolkit tech support channel along with some cmd screenshots, I'll have a look
Nguyen Le Minh
2025-07-27 10:59:35 +0000 UTCGreat model, got this working in LM Studio but having trouble linking it with Sugoi Toolkit v12.5, any chance for an updated/dedicated guide?
Arthur Kord
2025-07-27 09:04:04 +0000 UTCyou can quantize from the FP16 versions yourself with llama.cpp tool. I made a Q6 14B version like a month ago.
Amazing Flapples
2025-07-26 21:02:39 +0000 UTCIs there any chance we can get a less qauntized model q4 kinda hurts.
Gerald Gantos
2025-07-26 20:25:20 +0000 UTCHype
Amazing Flapples
2025-07-26 20:12:27 +0000 UTC
