What are the hardware requirements for GLM 5.3 EXL3 3.0bpw?

GLM 5.3 EXL3 3.0bpw requires approximately 293.3 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM 5.3 EXL3 3.0bpw and how large is it?

GLM 5.3 EXL3 3.0bpw is developed by 0xSero, a model with 146.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate GLM 5.3 EXL3 3.0bpw?

GLM 5.3 EXL3 3.0bpw is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 5.3 EXL3 3.0bpw by 0xSero — VRAM 293.3GB, 1024K context

Name: GLM 5.3 EXL3 3.0bpw
Author: 0xSero

GLM 5.3 EXL3 3.0bpw is an open-source language model by 0xSero. Features: 146.3b LLM, VRAM: 293.3GB, Context: 1024K, License: other, MoE, LLM Explorer Score: 0.28.

Arxiv:2510.13999 3-bit Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3 Conversational Exl3 Glm Glm-5.3 Glm moe dsa Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/0xSero/GLM-5.3-EXL3-3.0bpw

GLM 5.3 EXL3 3.0bpw Parameters and Internals

LLM Name	GLM 5.3 EXL3 3.0bpw
Repository 🤗	https://huggingface.co/0xSero/GLM-5.3-EXL3-3.0bpw
Base Model(s)	zai-org/GLM-5.3 zai-org/GLM-5.3
Model Size	146.3b
Required VRAM	293.3 GB
Updated	2026-11-04
Maintainer	0xSero
Model Type	glm_moe_dsa
Model Files	6.4 GB: 1-of-39 7.6 GB: 2-of-39 7.6 GB: 3-of-39 7.6 GB: 4-of-39 7.6 GB: 5-of-39 7.6 GB: 6-of-39 7.6 GB: 7-of-39 7.6 GB: 8-of-39 7.6 GB: 9-of-39 7.6 GB: 10-of-39 7.6 GB: 11-of-39 7.6 GB: 12-of-39 7.6 GB: 13-of-39 7.6 GB: 14-of-39 7.6 GB: 15-of-39 7.6 GB: 16-of-39 7.6 GB: 17-of-39 7.6 GB: 18-of-39 7.6 GB: 19-of-39 7.6 GB: 20-of-39 7.6 GB: 21-of-39 7.6 GB: 22-of-39 7.6 GB: 23-of-39 7.6 GB: 24-of-39 7.6 GB: 25-of-39 7.6 GB: 26-of-39 7.6 GB: 27-of-39 7.6 GB: 28-of-39 7.6 GB: 29-of-39 7.6 GB: 30-of-39 7.6 GB: 31-of-39 7.6 GB: 32-of-39 7.6 GB: 33-of-39 7.6 GB: 34-of-39 7.6 GB: 35-of-39 7.6 GB: 36-of-39 7.6 GB: 37-of-39 8.3 GB: 38-of-39 5.0 GB: 39-of-39
Model Architecture	GlmMoeDsaForCausalLM
License	other
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.15.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Vocabulary Size	154880

Rank the GLM 5.3 EXL3 3.0bpw capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to GLM 5.3 EXL3 3.0bpw

Best Alternatives	Context / RAM	Downloads	Likes
GLM 5.3 UNCENSORED EXL3 3.0bpw	1024K / 293.4 GB	1342	227
GLM 5.3 UNCENSORED EXL3 3.0bpw	1024K / 293.4 GB	295	1
GLM 5.3 UNCENSORED EXL3 3.0bpw	1024K / 293.4 GB	201	1
GLM 5.3 UNCENSORED EXL3 3.0bpw	1024K / 293.4 GB	40	1

Note: green Score (e.g. "73.2") means that the model is better than 0xSero/GLM-5.3-EXL3-3.0bpw.