voxprint t lite it 2.1 needs about 5.6 GB of memory at IQ4_XS (a 4.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 0.0 GB to 5.9 GB (Q5_K_M).
Voxprint t-lite-it-2.1 – 8.19B Qwen3 model with tool‑calling
Voxprint t-lite-it-2.1 is an 8.19B‑parameter Qwen3 model optimized for instruction following and tool‑calling. It is built on t-tech/T-lite-it-2.1 and trained with 40B instruction tokens and ~670K supervised examples. The model is released under apache‑2.0.
Good at
- Tool‑calling workflows
- Instruction following
- Russian text generation
Limits
- No vision support
- Requires non‑thinking mode
- No generation of ` ` in output
Best for
- Agentic applications needing tool use
- Chatbots with Russian language focus
- Instruction‑driven workflows
Who it’s for. Developers building Russian‑language agents that need reliable tool‑calling. The model is suitable for industrial or commercial use where the user can enforce safety and oversight.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 5.6 GB | Fits | Get file → | |
| Q5_K_M | 5.9 GB | 7.1 GB | Fits | Get file → |
For 8 GB VRAM, use the IQ4_XS quant (file size 4.56 GB, memory 5.6 GB at 8 k context). For 16 GB VRAM, Q5_K_M (5.85 GB, 7.1 GB). The unknown quant is too small to estimate memory. All estimates are approximate.
What GPU do you need for voxprint t lite it 2.1?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is IQ4_XS (4.6 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.1 GB in use).
Which voxprint t lite it 2.1 quant should you choose?
IQ4_XS (4.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about voxprint t lite it 2.1
How much VRAM does voxprint t lite it 2.1 need?
About 5.6 GB at IQ4_XS with an 8K context window. That is the 4.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run voxprint t lite it 2.1 on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of voxprint t lite it 2.1 GGUF?
It depends on the quant: file is 0.0 GB, IQ4_XS is 4.6 GB, Q5_K_M is 5.9 GB.
What context length does voxprint t lite it 2.1 support?
The GGUF header lists a trained context length of 40,960 tokens (40K).
Where can I download voxprint t lite it 2.1 GGUF?
The files are on Hugging Face in the Mitroshenkov87/voxprint-t-lite-it-2.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does voxprint t lite it 2.1 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Voxprint t-lite-it-2.1 on 8 GB VRAM?
Yes, using the IQ4_XS quant which requires 5.6 GB at 8 k context. The model will fit within 8 GB VRAM.
Does the model support vision tasks?
No, the model does not support vision. It is text‑only.
What license applies to this model?
The model is released under the apache‑2.0 license.