NexVeridian/GLM-4.5-Air-5bit

This model NexVeridian/GLM-4.5-Air-5bit was converted to MLX format from zai-org/GLM-4.5-Air using mlx-lm version 0.26.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/GLM-4.5-Air-5bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
Downloads last month
40
Safetensors
Model size
107B params
Tensor type
BF16
U32
F32
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for NexVeridian/GLM-4.5-Air-5bit

Quantized
(52)
this model