BO

boto-27B

BotoGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters27.2B
Context8K
Layers46
Architecturegemma2
Smallest quant6.1 GB
Quick answer

boto-27B needs about 20.2 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 6.1 GB (IQ1_S) to 22.3 GB (Q6_K).

Boto 27B – a 27.2B‑parameter Gemma2 fine‑tuned for Portuguese

Boto 27B is a 27.2B‑parameter Gemma2 model fine‑tuned for Portuguese. It produces verbose responses and is licensed under apache-2.0. The model is available in multiple GGUF quantizations.

Good at

  • Portuguese text generation
  • Verbose responses
  • Fine‑tuned language model

Limits

  • Large context size of 8192 tokens
  • Requires significant VRAM for higher‑quality quants
  • No vision support

Best for

  • Chatbots needing Portuguese support
  • Content creation in Portuguese
  • Research on fine‑tuned language models

Who it’s for. Developers and researchers who need a large Portuguese language model for local inference. The model is suitable for those with sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S6.1 GB 9.7 GB
Too big Get file →
IQ1_M6.7 GB 10.3 GB
Too big Get file →
IQ2_XXS7.6 GB 11.2 GB
Too big Get file →
IQ2_XS8.4 GB 12.0 GB
Too big Get file →
IQ2_S8.7 GB 12.2 GB
Too big Get file →
IQ2_M9.4 GB 13.0 GB
Too big Get file →
Q2_K10.4 GB 14.0 GB
Too big Get file →
IQ3_XXS10.8 GB 14.3 GB
Too big Get file →
IQ3_XS11.6 GB 15.1 GB
Too big Get file →
IQ3_S12.2 GB 15.8 GB
Too big Get file →
Q3_K_S12.2 GB 15.8 GB
Too big Get file →
IQ3_M12.5 GB 16.0 GB
Too big Get file →
Q3_K_M13.4 GB 17.0 GB
Too big Get file →
Q3_K_L14.5 GB 18.1 GB
Too big Get file →
IQ4_XS14.8 GB 18.4 GB
Too big Get file →
Q4_015.7 GB 19.3 GB
Too big Get file →
Q4_K_S15.7 GB 19.3 GB
Too big Get file →
Q4_K_M16.6 GB 20.2 GB
Too big Get file →
Q5_K_S18.9 GB 22.5 GB
Too big Get file →
Q5_K_M19.4 GB 23.0 GB
Too big Get file →
Q6_K22.3 GB 25.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.13 GB file, 9.7 GB memory). For 12 GB VRAM, IQ2_XS (8.4 GB file, 12 GB memory) or Q2_K (10.45 GB file, 14 GB memory). For 16 GB VRAM, Q3_K_M (13.42 GB file, 17 GB memory) or Q4_K_M (16.65 GB file, 20.2 GB memory).

What GPU do you need for boto-27B?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_XS (8.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (12.5 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.3 GB file, about 25.9 GB in use).

Which boto-27B quant should you choose?

Q4_K_M is the usual starting point for boto-27B: it balances file size and quality well. Here it is a 16.6 GB file.

If memory is tight, the smallest file is IQ1_S at 6.1 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

Architecturegemma2
Parameters27.2B
Layers46
Trained context8,192 tokens
KV cache (fp16)368 KB per token

Source

Quantized bymradermacher
FamilyBoto
Licenseapache-2.0
Downloads (HF)1,572
Last updated2024-08-02

Frequently asked questions about boto-27B

How much VRAM does boto-27B need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 16.6 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 boto-27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of boto-27B GGUF?

It depends on the quant: IQ1_S is 6.1 GB, IQ1_M is 6.7 GB, IQ2_XXS is 7.6 GB, IQ2_XS is 8.4 GB, IQ2_S is 8.7 GB, IQ2_M is 9.4 GB and 15 more.

What context length does boto-27B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.

Where can I download boto-27B GGUF?

The files are on Hugging Face in the mradermacher/boto-27B-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 boto-27B 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 Boto 27B on 8 GB VRAM?

Yes, use the IQ1_S quant which requires about 9.7 GB of VRAM at 8 k context.

Does Boto 27B support vision tasks?

No, the model has no vision capabilities.

What license applies to Boto 27B?

The model is released under the apache-2.0 license.

Other GGUFs of boto-27B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Boto models

All Boto →

Other medium models

All medium models →