TO

TowerBase 7B v0.1

TowerbaseGGUF by mradermacherUpdated 2024-12-04
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

TowerBase 7B v0.1 needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 1.5 GB (IQ1_S) to 5.5 GB (Q6_K).

TowerBase 7B v0.1 – a 6.74B multilingual LLM in GGUF format

TowerBase 7B v0.1 is a 6.74B parameter model built on Llama 2 and fine‑tuned on 20B tokens of multilingual data. It supports English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, and Russian. The model is released under CC‑BY‑NC‑4.0.

Good at

  • Translation in supported languages
  • Few‑shot multilingual tasks
  • Fine‑tuning for APE and GEC

Limits

  • No vision support
  • Not aligned to human preferences
  • Limited to the 10 supported languages

Best for

  • Research on multilingual translation
  • Fine‑tuning for language‑specific tasks
  • Zero‑shot multilingual inference

Who it’s for. Researchers and developers working on multilingual NLP who need a 7B‑scale model for translation, APE, or GEC tasks. The model is suitable for fine‑tuning and few‑shot inference in the ten supported languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 4.2 GB
Fits Get file →
IQ1_M1.7 GB 4.3 GB
Fits Get file →
IQ2_XXS1.9 GB 4.5 GB
Fits Get file →
IQ2_XS2.0 GB 4.7 GB
Fits Get file →
IQ2_S2.2 GB 4.8 GB
Fits Get file →
Q2_K_S2.3 GB 5.0 GB
Fits Get file →
IQ2_M2.4 GB 5.0 GB
Fits Get file →
Q2_K2.5 GB 5.2 GB
Fits Get file →
IQ3_XXS2.6 GB 5.2 GB
Fits Get file →
IQ3_XS2.8 GB 5.4 GB
Fits Get file →
IQ3_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
IQ3_M3.1 GB 5.8 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
IQ4_XS3.6 GB 6.3 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (1.53 GB, 6.3 GB memory) or IQ1_M (1.65 GB, 6.4 GB memory). With 12 GB VRAM, IQ2_S (2.2 GB, 7 GB memory) or Q2_K_S (2.32 GB, 7.1 GB memory) are suitable. For 16 GB VRAM, Q4_K_M (4.08 GB, 8.9 GB memory) or Q5_K_S (4.65 GB, 9.4 GB memory) provide higher quality.

What GPU do you need for TowerBase 7B v0.1?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).

Which TowerBase 7B v0.1 quant should you choose?

Q4_K_M is the usual starting point for TowerBase 7B v0.1: it balances file size and quality well. Here it is a 4.1 GB file.

If memory is tight, the smallest file is IQ1_S at 1.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyTowerbase
Downloads (HF)814
Last updated2024-12-04

Frequently asked questions about TowerBase 7B v0.1

How much VRAM does TowerBase 7B v0.1 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 TowerBase 7B v0.1 on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TowerBase 7B v0.1 GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, Q2_K_S is 2.3 GB and 19 more.

What context length does TowerBase 7B v0.1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download TowerBase 7B v0.1 GGUF?

The files are on Hugging Face in the mradermacher/TowerBase-7B-v0.1-i1-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 TowerBase 7B v0.1 use?

Hugging Face lists the license as cc-by-nc-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 TowerBase 7B v0.1 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which require about 6.3–6.4 GB memory at 8k context.

Does the model support image inputs?

No, TowerBase 7B v0.1 is a text‑only language model.

Is the model aligned to user preferences?

No, the model is not aligned and may generate hallucinations or harmful content.

Other GGUFs of TowerBase-7B-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Towerbase models

All Towerbase →

Other small models

All small models →