MA

Manaca 1b Base

ManacaGGUF by mradermacherUpdated 2026-09-24
Download on Hugging Face
Parameters1.72B
Context4K
Layers24
Architecturellama
Smallest quant0.0 GB
Quick answer

Manaca 1b Base needs about 2.0 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.4 GB (Q6_K).

Manaca 1b Base – 1.72B‑parameter Brazilian Portuguese LLM

Manaca 1b Base is a decoder‑only Llama‑style model trained from scratch for Brazilian Portuguese. It contains ~1.72B parameters and is a base, pre‑trained model without instruction tuning or alignment. The model is released under cc‑by‑4.0.

Good at

  • Brazilian Portuguese text generation
  • Low‑resource inference on modest GPUs
  • Reproducible training pipeline

Limits

  • No instruction tuning or alignment
  • No vision support
  • Requires 8k context for memory estimates

Best for

  • Local inference on 8–16 GB VRAM
  • Research on Brazilian Portuguese language models
  • Educational demonstrations of Llama‑style decoders

Who it’s for. Researchers and developers needing a Brazilian Portuguese language model that can run locally. The model is suitable for experimentation, fine‑tuning, or deployment in environments with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.7 GB
Fits Get file →
IQ1_S0.4 GB 1.1 GB
Fits Get file →
IQ1_M0.5 GB 1.2 GB
Fits Get file →
IQ2_XXS0.5 GB 1.2 GB
Fits Get file →
IQ2_XS0.6 GB 1.3 GB
Fits Get file →
IQ2_S0.6 GB 1.3 GB
Fits Get file →
IQ2_M0.6 GB 1.3 GB
Fits Get file →
Q2_K_S0.7 GB 1.4 GB
Fits Get file →
Q2_K0.7 GB 1.4 GB
Fits Get file →
IQ3_XXS0.7 GB 1.4 GB
Fits Get file →
IQ3_XS0.8 GB 1.5 GB
Fits Get file →
Q3_K_S0.8 GB 1.5 GB
Fits Get file →
IQ3_S0.8 GB 1.5 GB
Fits Get file →
IQ3_M0.8 GB 1.5 GB
Fits Get file →
Q3_K_M0.9 GB 1.6 GB
Fits Get file →
Q3_K_L0.9 GB 1.6 GB
Fits Get file →
IQ4_XS1.0 GB 1.7 GB
Fits Get file →
IQ4_NL1.0 GB 1.7 GB
Fits Get file →
Q4_01.0 GB 1.7 GB
Fits Get file →
Q4_K_S1.0 GB 1.7 GB
Fits Get file →
Q4_K_M1.1 GB 1.8 GB
Fits Get file →
Q4_11.1 GB 1.8 GB
Fits Get file →
Q5_K_S1.2 GB 1.9 GB
Fits Get file →
Q5_K_M1.2 GB 1.9 GB
Fits Get file →
Q6_K1.4 GB 2.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.06 GB, ~2.0 GB memory). For 12 GB VRAM, Q5_K_M (1.23 GB, ~2.1 GB memory) or Q6_K (1.42 GB, ~2.3 GB memory). For 4 GB VRAM, IQ1_S (0.45 GB, ~1.3 GB memory) is the smallest viable quant.

What GPU do you need for Manaca 1b Base?

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 Q6_K (1.4 GB file, about 2.3 GB in use).

Which Manaca 1b Base quant should you choose?

Q4_K_M is the usual starting point for Manaca 1b Base: it balances file size and quality well. Here it is a 1.1 GB file.

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
Parameters1.72B
Layers24
Trained context4,096 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyManaca
Licensecc-by-4.0
Downloads (HF)725
Last updated2026-09-24

Frequently asked questions about Manaca 1b Base

How much VRAM does Manaca 1b Base need?

About 2.0 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Manaca 1b Base on an 8 GB GPU?

Yes, with Q6_K: the 1.4 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Manaca 1b Base GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB and 19 more.

What context length does Manaca 1b Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.2 GB at 4K.

Where can I download Manaca 1b Base GGUF?

The files are on Hugging Face in the mradermacher/manaca-1b-base-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 Manaca 1b Base 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 this model on 8 GB VRAM?

Yes, a Q4_K_M quant requires about 2.0 GB VRAM at 8k context, which fits within 8 GB.

Does the model support English?

The model was trained for Brazilian Portuguese; it can process English but is not optimized for it.

Is the model instruction‑tuned?

No, it is a base model and does not follow instructions or engage in conversation.

Other GGUFs of manaca-1b-base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Manaca models

All Manaca →

Other tiny models

All tiny models →