second_constantine/
t-pro-it-2.1:32b

9 4 days ago

T-pro-it-2.1 — is an efficient russian model built upon the Qwen 3 model family with improved instruction following and tool-calling capabilities (quantized Q4_K_M)

tools thinking 32b

4 days ago

27b0e8849683 · 20GB ·

model
qwen3
·
32.8B
·
Q4_K_M
template
{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la
params
{ "repeat_penalty": 1, "stop": [ "<|im_start|>", "<|im_end|>" ], "te

Readme

Based on https://huggingface.co/t-tech/T-pro-it-2.1-GGUF

Release https://habr.com/ru/companies/tbank/articles/979650/

Feature Value
vision false
thinking true
tools true
Device Speed, token/s Context VRAM, gb Versions
RTX 3090 24gb ~36 4096 21 Q4_K_M,0.12.2
RTX 3090 24gb ~36 15360 24 Q4_K_M,0.12.2