Aion-1.0-Instruct-2.3B โ€” MLX 8bit

Quantized to 8 bits per weight.

Converted from microsoft/Aion-1.0-Instruct-2.3B using mlx-lm.

Requirements

The bloom model type is support in my mlx-lm fork(AlphaKure/mlx-lm.

Until test finish. I will send a PR to offical repo.

Update at: 2026/11/19

pip install git+https://github.com/AlphaKure/mlx-lm.git@9d7b7fada7732228f46821cc80e32d69ee3f47df

Use

mlx_lm.generate --model AlphaOxO/Aion-1.0-Instruct-2.3B-8bits-mlx --prompt "hello"
from mlx_lm import load, generate

model, tokenizer = load("AlphaOxO/Aion-1.0-Instruct-2.3B-8bits-mlx")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "hello"}], add_generation_prompt=True
)
print(generate(model, tokenizer, prompt=prompt))
Downloads last month
-
Safetensors
Model size
2B params
Tensor type
U32
ยท
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for AlphaOxO/Aion-1.0-Instruct-2.3B-8bits-mlx

Quantized
(4)
this model

Collection including AlphaOxO/Aion-1.0-Instruct-2.3B-8bits-mlx