TI

TildeOpen 30b

TildeopenGGUF by bartowskiUpdated 2025-09-08
Download on Hugging Face
Parameters30.7B
Context64K
Layers60
Architecturellama
Smallest quant0.0 GB
Quick answer

TildeOpen 30b needs about 21.1 GB of memory at Q4_K_M (a 18.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.0 GB to 61.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

TildeOpen 30b – a 30.7B parameter dense decoder-only transformer

TildeOpen 30b is a 30.7B parameter dense decoder-only transformer trained on 2 trillion tokens. It supports 30 European languages, programming code, mathematical proofs, and XML translation data. The model is released under CC‑BY‑4.0 and is not yet instruction‑tuned or safety‑aligned.

Good at

  • Multilingual support for 30 European languages
  • Large context window of 65536 tokens
  • Dense transformer architecture for general text generation

Limits

  • No instruction tuning or safety alignment
  • No vision or multimodal support
  • Requires significant VRAM for higher‑quality quants

Best for

  • Research on underrepresented European languages
  • Baseline for building specialized translation models
  • Large‑context text generation tasks

Who it’s for. Researchers and developers needing a large multilingual foundation model for European languages. The model is open‑source and suitable for building specialized translation or language‑specific applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.5 GB
Fits Get file →
IQ2_XXS8.5 GB 11.0 GB
Too big Get file →
IQ2_XS9.4 GB 11.9 GB
Too big Get file →
IQ2_S9.9 GB 12.4 GB
Too big Get file →
IQ2_M10.7 GB 13.2 GB
Too big Get file →
Q2_K11.6 GB 14.1 GB
Too big Get file →
IQ3_XXS12.0 GB 14.6 GB
Too big Get file →
Q2_K_L12.4 GB 14.9 GB
Too big Get file →
IQ3_XS12.9 GB 15.4 GB
Too big Get file →
Q3_K_S13.5 GB 16.0 GB
Too big Get file →
IQ3_M14.0 GB 16.5 GB
Too big Get file →
Q3_K_M15.0 GB 17.5 GB
Too big Get file →
Q3_K_L16.2 GB 18.7 GB
Too big Get file →
IQ4_XS16.6 GB 19.1 GB
Too big Get file →
Q3_K_XL16.9 GB 19.4 GB
Too big Get file →
IQ4_NL17.5 GB 20.0 GB
Too big Get file →
Q4_017.5 GB 20.0 GB
Too big Get file →
Q4_K_S17.6 GB 20.1 GB
Too big Get file →
Q4_K_M18.5 GB 21.1 GB
Too big Get file →
Q4_K_L19.1 GB 21.7 GB
Too big Get file →
Q4_119.3 GB 21.9 GB
Too big Get file →
Q5_K_S21.2 GB 23.7 GB
Too big Get file →
Q5_K_M21.8 GB 24.3 GB
Too big Get file →
Q5_K_L22.3 GB 24.8 GB
Too big Get file →
Q6_K25.2 GB 27.7 GB
Too big Get file →
Q6_K_L25.6 GB 28.1 GB
Too big Get file →
Q8_032.6 GB 35.1 GB
Too big Get file →
BF1661.4 GB (2 parts) 63.9 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (8.5 GB file, ~11 GB memory at 8k context). For 16 GB VRAM, IQ4_K_M (18.54 GB file, ~21.1 GB memory) or Q4_K_L (19.14 GB file, ~21.7 GB memory). For 32 GB VRAM, Q8_0 (32.6 GB file, ~35.1 GB memory) or BF16 split into shards. Memory estimates are approximate.

What GPU do you need for TildeOpen 30b?

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: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XS (9.4 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_S (13.5 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_S (21.2 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (25.6 GB file, about 28.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.6 GB file, about 35.1 GB in use).

Which TildeOpen 30b quant should you choose?

Q4_K_M is the usual starting point for TildeOpen 30b: it balances file size and quality well. Here it is a 18.5 GB file.

The Q8_0 file is 32.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

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

Architecturellama
Parameters30.7B
Layers60
Trained context65,536 tokens
KV cache (fp16)240 KB per token

Source

Quantized bybartowski
FamilyTildeopen
Licensecc-by-4.0
Downloads (HF)784
Last updated2025-09-08

Frequently asked questions about TildeOpen 30b

How much VRAM does TildeOpen 30b need?

About 21.1 GB at Q4_K_M with an 8K context window. That is the 18.5 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 TildeOpen 30b on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TildeOpen 30b GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 8.5 GB, IQ2_XS is 9.4 GB, IQ2_S is 9.9 GB, IQ2_M is 10.7 GB, Q2_K is 11.6 GB and 22 more.

What context length does TildeOpen 30b support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download TildeOpen 30b GGUF?

The files are on Hugging Face in the bartowski/TildeAI_TildeOpen-30b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does TildeOpen 30b use?

Hugging Face lists the license as cc-by-4.0. 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 TildeOpen 30b on 8 GB VRAM?

Use the IQ2_XXS quant, which is 8.5 GB and requires about 11 GB of VRAM at 8k context.

Does the model support image input?

No, TildeOpen 30b is a text‑only decoder‑only transformer with no vision capability.

Is the model aligned with safety guidelines?

No, the base model is not instruction‑tuned or safety‑aligned; future specialized versions may include alignment.

Other GGUFs of TildeOpen-30b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Tildeopen models

All Tildeopen →

Other medium models

All medium models →