Capa

NBR-1B-Portuguese-MCQ MLX 4-bit

This is limajr/NBR-1B-Portuguese-MCQ, a Portuguese language model, converted to 4-bit MLX so it can run with mlx-lm (size in the Files table below). I only tested it on the MLX CPU backend on Linux, not on Apple Silicon.

pip install mlx-lm
mlx_lm.generate --model guicybercode/NBR-1B-Portuguese-MCQ-mlx-4bit --prompt "A capital do Brasil é" --max-tokens 32 --temp 0

All credit for the model goes to the original authors, limajr. I only converted the format. License: Apache-2.0, same as the original.

Versão quantizada do modelo limajr/NBR-1B-Portuguese-MCQ para uso local; todo o crédito é dos autores originais.

Files

File Quantization Size
model.safetensors 4-bit (group size 64), non-quantized tensors in float16 720 MB (720142694 bytes)

How this was made

mlx-lm 0.32.2 with mlx 0.32.4 (CPU backend, Linux x86_64):

mlx_lm.convert --hf-path limajr/NBR-1B-Portuguese-MCQ --mlx-path NBR-1B-Portuguese-MCQ-mlx-4bit -q --q-bits 4 --dtype float16

--dtype float16 was used because, on the MLX CPU backend on Linux, a bfloat16 conversion produced only <unk> tokens in testing, while float16 produced normal text. Not tested on Apple Silicon.

Usage

pip install mlx-lm
mlx_lm.generate --model guicybercode/NBR-1B-Portuguese-MCQ-mlx-4bit --prompt "A capital do Brasil é" --max-tokens 32 --temp 0

Smoke test

Prompt: A capital do Brasil é, 32 tokens, temperature 0, run on the MLX CPU backend on Linux. Only a load-and-generate check, not an evaluation.

metadesde R$ 291.790 por

No benchmarks were run on this quantized model. See the original model card for the authors' evaluations and intended use.

Downloads last month
24
Safetensors
Model size
1B params
Tensor type
U32
·
F16
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for guicybercode/NBR-1B-Portuguese-MCQ-mlx-4bit

Quantized
(2)
this model