Downloads · 30 days
198
16% of all-time downloads
Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit-split-mtp
rayray916/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit-split-mtp
Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit-split-mtp is a text generation model from rayray916. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
The Model Eldadalbajob/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit was converted to MLX format from huihui-ai/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated using mlx-lm version 0.28.3.
All-time downloads
1.2K
Public
Parameters
79.8B
38.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors38.2 GB · 100%
Parameter types
How the weights are stored.
U3279.8B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Eldadalbajob/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit
The Model Eldadalbajob/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit was converted to MLX format from huihui-ai/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Eldadalbajob/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_5_moe
- License
- mit
- Languages
- en, zh
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026