What are the hardware requirements for GLM 5.2 NVFP4 DFlash Ko?

GLM 5.2 NVFP4 DFlash Ko requires approximately 3.6 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 5.2 NVFP4 DFlash Ko and how large is it?

GLM 5.2 NVFP4 DFlash Ko is developed by lablup, a model with 1.8b 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 5.2 NVFP4 DFlash Ko?

GLM 5.2 NVFP4 DFlash Ko is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 5.2 NVFP4 DFlash Ko by lablup — VRAM 3.6GB, 1024K context

Name: GLM 5.2 NVFP4 DFlash Ko
Author: lablup

GLM 5.2 NVFP4 DFlash Ko is an open-source language model by lablup. Features: 1.8b LLM, VRAM: 3.6GB, Context: 1024K, License: mit, LLM Explorer Score: 0.27.

Arxiv:2602.06036 Agentic Base model:finetune:nvidia/glm... Base model:nvidia/glm-5.2-nvfp... Custom code Dflash Draft-model En Endpoints compatible Feature-extraction Ko Korean Qwen3 Region:us Safetensors Speculative-decoding Tool-calling Vllm

Model Card on HF 🤗: https://huggingface.co/lablup/GLM-5.2-NVFP4-DFlash-ko

GLM 5.2 NVFP4 DFlash Ko Parameters and Internals

LLM Name	GLM 5.2 NVFP4 DFlash Ko
Repository 🤗	https://huggingface.co/lablup/GLM-5.2-NVFP4-DFlash-ko
Base Model(s)	nvidia/GLM-5.2-NVFP4 nvidia/GLM-5.2-NVFP4
Model Size	1.8b
Required VRAM	3.6 GB
Updated	2026-10-22
Maintainer	lablup
Model Type	qwen3
Model Files	3.6 GB
Supported Languages	ko en
Model Architecture	DFlashDraftModel
License	mit
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.12.0
Vocabulary Size	154880

Rank the GLM 5.2 NVFP4 DFlash Ko 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 5.2 NVFP4 DFlash Ko

Best Alternatives	Context / RAM	Downloads	Likes
MiniMax M2.5 DFlash	192K / 3.6 GB	124	9

Note: green Score (e.g. "73.2") means that the model is better than lablup/GLM-5.2-NVFP4-DFlash-ko.