LI

T Lite It 1.0

LiteGGUF by aovchinnikovUpdated 2024-12-11
Download on Hugging Face
Parameters7.6B
Context32K
Layers28
Architectureqwen2
Smallest quant4.7 GB
Quick answer

T Lite It 1.0 needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

T Lite It 1.0 – a 7.6B Qwen2-based model for fine‑tuning

T Lite It 1.0 is a 7.6B parameter Qwen2 model designed for further fine‑tuning. It was trained on 100B tokens of Russian data, 40B tokens of instruction data, and 1B tokens of supervised and preference tuning. The model is not intended as a ready‑to‑use conversational assistant.

Good at

  • Fine‑tuning on custom datasets
  • Instruction following
  • Alignment techniques

Limits

  • Not a ready‑to‑use assistant
  • No license specified
  • No vision support

Best for

  • Custom chatbot development
  • Research prototyping
  • Data‑driven fine‑tuning

Who it’s for. Developers and researchers who want a lightweight Qwen2 model to adapt for specific tasks. The model requires careful oversight and additional training to meet safety standards.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.7 GB 5.7 GB
Fits Get file →

The Q4_K_M quantization yields a 4.68 GB file and requires approximately 5.7 GB of VRAM at 8 k context. This is suitable for systems with at least 8 GB of VRAM. For lower VRAM budgets, a higher‑quantization variant would be needed, but none is listed.

What GPU do you need for T Lite It 1.0?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).

Which T Lite It 1.0 quant should you choose?

Q4_K_M is the usual starting point for T Lite It 1.0: it balances file size and quality well. Here it is a 4.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters7.6B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byaovchinnikov
FamilyLite
Downloads (HF)3,399
Last updated2024-12-11

Frequently asked questions about T Lite It 1.0

How much VRAM does T Lite It 1.0 need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 T Lite It 1.0 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of T Lite It 1.0 GGUF?

It depends on the quant: Q4_K_M is 4.7 GB.

What context length does T Lite It 1.0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download T Lite It 1.0 GGUF?

The files are on Hugging Face in the aovchinnikov/T-lite-it-1.0-Q4_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run T Lite It 1.0 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 5.7 GB of VRAM at 8 k context, which fits within an 8 GB VRAM budget.

Is T Lite It 1.0 ready for production use?

No, the model is intended for fine‑tuning and requires additional training and oversight before deployment.

Other GGUFs of T-lite-it-1.0

Similar models

Browse all →

More Lite models

All Lite →

Other small models

All small models →