Downloads · 30 days
11
4% of all-time downloads
Mixtral-8x7B-AQLM-4Bit-4x8-hf
dbw6/Mixtral-8x7B-AQLM-4Bit-4x8-hf
Mixtral-8x7B-AQLM-4Bit-4x8-hf is a text generation model from dbw6. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This repository contains a Hugging Face export of Mixtral-8x7B-v0.1 quantized with AQLM using the 4-bit 4x8 scheme.
All-time downloads
284
Public
Parameters
23.5B
23.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors23.8 GB · 100%
Parameter types
How the weights are stored.
I823.2B · 99%
Try a prompt
Base models
Model card
From the Hugging Face model README
dbw6/Mixtral-8x7B-AQLM-4Bit-4x8-hf
This repository contains a Hugging Face export of Mixtral-8x7B-v0.1 quantized with AQLM using the 4-bit 4x8 scheme.
Base model
mistralai/Mixtral-8x7B-v0.1
Quantization
- Method:
AQLM - Scheme:
4x8 - Effective label:
4-bit - Source checkpoint:
/work/bduan1/quantized_models/Mixtral-8x7B-AQLM-4bit-4x8
Conversion
This repo was produced with convert_to_hf.py from the AQLM project, then exported with --save_safetensors and --save_tokenizer.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "dbw6/Mixtral-8x7B-AQLM-4Bit-4x8-hf"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
trust_remote_code=True,
)
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- License
- apache-2.0
- Languages
- en
- Created
- Mar 30, 2026
- Updated
- Mar 30, 2026