SA

sabia-7b

SabiaGGUF by RichardErkhovUpdated 2024-06-01
Download on Hugging Face
Parameters6.74B
Context2K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

sabia-7b 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 22 quants, from 2.5 GB (Q2_K) to 5.5 GB (Q6_K).

sabia-7b – a 6.74B parameter llama model

sabia-7b is a 6.74B parameter llama architecture model. It was quantized by RichardErkhov and is available in multiple GGUF formats. The model was trained on a 2048 token context window.

Good at

  • Text generation in Portuguese
  • Educational content generation
  • Language modeling tasks

Limits

  • No vision support
  • No license information provided
  • Context limited to 2048 tokens

Best for

  • Generating short Portuguese texts
  • Creating educational quizzes
  • Fine‑tuning on Portuguese corpora

Who it’s for. Developers looking for a lightweight Portuguese language model for text generation. Researchers needing a 6.74B parameter model with multiple quantization options.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 4.1 GB
Fits Get file →
IQ3_XS2.8 GB 4.4 GB
Fits Get file →
IQ3_S2.9 GB 4.5 GB
Fits Get file →
Q3_K_S2.9 GB 4.5 GB
Fits Get file →
IQ3_M3.1 GB 4.7 GB
Fits Get file →
Q3_K3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_L3.6 GB 5.2 GB
Fits Get file →
IQ4_XS3.6 GB 5.2 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
IQ4_NL3.8 GB 5.4 GB
Fits Get file →
Q4_K_S3.9 GB 5.4 GB
Fits Get file →
Q4_K4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.1 GB 5.7 GB
Fits Get file →
Q4_14.2 GB 5.8 GB
Fits Get file →
Q5_04.7 GB 6.2 GB
Fits Get file →
Q5_K_S4.7 GB 6.2 GB
Fits Get file →
Q5_K4.8 GB 6.4 GB
Fits Get file →
Q5_K_M4.8 GB 6.4 GB
Fits Get file →
Q5_15.1 GB 6.6 GB
Fits Get file →
Q8_05.2 GB 6.8 GB
Fits Get file →
Q6_K5.5 GB 7.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.08 GB, estimated 8.9 GB memory). For 12 GB VRAM, Q5_K_M (file size 4.78 GB, estimated 9.6 GB memory) is suitable. For 16 GB VRAM, Q6_K (file size 5.53 GB, estimated 10.3 GB memory) provides higher quality.

What GPU do you need for sabia-7b?

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 sabia-7b quant should you choose?

Q4_K_M is the usual starting point for sabia-7b: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 5.2 GB, about 1.3 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 Q2_K at 2.5 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 context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
FamilySabia
Downloads (HF)556
Last updated2024-06-01

Frequently asked questions about sabia-7b

How much VRAM does sabia-7b 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 sabia-7b 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 sabia-7b GGUF?

It depends on the quant: Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB, IQ3_M is 3.1 GB, Q3_K is 3.3 GB and 16 more.

What context length does sabia-7b support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download sabia-7b GGUF?

The files are on Hugging Face in the RichardErkhov/maritaca-ai_-_sabia-7b-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 Q4_K_M on 8 GB VRAM?

Yes, Q4_K_M requires about 8.9 GB memory at 8k context, which fits in 8 GB VRAM with some overhead.

Is there a license for this model?

No license information is provided in the supplied data.

Does the model support vision tasks?

No, the model has no vision support.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Sabia models

All Sabia →

Other small models

All small models →