T-pro-it-2.0-GGUF

🚨 Users are advised to exercise caution and are responsible for any additional training and oversight required to ensure the model's responses meet acceptable ethical and safety standards. The responsibility for incorporating this model into industrial or commercial solutions lies entirely with those who choose to deploy it.

This repository contains T-pro-it-2.0 converted to the GGUF format with llama.cpp.
See the original BF16 model here: t-tech/T-pro-it-2.0.

📊 Benchmarks

TBD

Available quantisations

Recommendation: choose the highest-quality quantisation that fits your hardware (VRAM / RAM).

Filename (→ -gguf)	Quant method	Bits	Size (GB)
t-pro-it-2.0-q2_k	Q2_K	2	12.3
t-pro-it-2.0-iq3_xs	IQ3_XS	3	13.7
t-pro-it-2.0-iq3_s	IQ3_S	3	14.4
t-pro-it-2.0-q3_k_s	Q3_K_S	3	14.4
t-pro-it-2.0-q3_k_m	Q3_K_M	3	16.0
t-pro-it-2.0-iq4_xs	IQ4_XS	4	17.9
t-pro-it-2.0-q4_k_s	Q4_K_S	4	18.8
t-pro-it-2.0-iq4_nl	IQ4_NL	4	18.8
t-pro-it-2.0-q4_0	Q4_0	4	18.6
t-pro-it-2.0-q4_k_m	Q4_K_M	4	19.8
t-pro-it-2.0-q5_k_s	Q5_K_S	5	22.6
t-pro-it-2.0-q5_0	Q5_0	5	22.6
t-pro-it-2.0-q5_k_m	Q5_K_M	5	23.2
t-pro-it-2.0-q6_k	Q6_K	6	26.9
t-pro-it-2.0-q8_0	Q8_0	8	34.8

Size figures assume no GPU off-loading. Off-loading lowers RAM usage and uses VRAM instead.

Quickstart

llama.cpp

Check out our llama.cpp documentation for more usage guide.

We advise you to clone llama.cpp and install it following the official guide. We follow the latest version of llama.cpp. In the following demonstration, we assume that you are running commands under the repository llama.cpp.

./llama-cli -hf t-tech/T-pro-it-2.0-GGUF:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --presence-penalty 1.0 -c 40960 -n 32768 --no-context-shift

ollama

Check out our ollama documentation for more usage guide.

You can run Qwen3 with one command:

ollama run hf.co/t-tech/T-pro-it-2.0-GGUF:Q8_0

Switching Between Thinking and Non-Thinking Mode

You can add /think and /no_think to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.