What are the hardware requirements for GLM 5 REAP 50pct FP8?

GLM 5 REAP 50pct FP8 requires approximately 223.3 GB of VRAM and supports a context window of 198K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM 5 REAP 50pct FP8 and how large is it?

GLM 5 REAP 50pct FP8 is developed by 0xSero, a model with 381.5b 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 REAP 50pct FP8?

GLM 5 REAP 50pct FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 5 REAP 50pct FP8 by 0xSero — VRAM 223.3GB, 198K context

Name: GLM 5 REAP 50pct FP8
Author: 0xSero

GLM 5 REAP 50pct FP8 is an open-source language model by 0xSero. Features: 381.5b LLM, VRAM: 223.3GB, Context: 198K, License: apache-2.0, MoE, LLM Explorer Score: 0.23.

Arxiv:2510.13999 Base model:quantized:zai-org/g... Base model:zai-org/glm-5 Compression Conversational Dataset:open-r1/mixture-of-tho... Dataset:salesforce/xlam-functi... Dataset:swe-bench/swe-smith-tr... Dataset:theblackcat102/evol-co... Endpoints compatible Expert-pruning Fp8 Glm Glm moe dsa Moe Pruned Reap Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/0xSero/GLM-5-REAP-50pct-FP8

GLM 5 REAP 50pct FP8 Parameters and Internals

LLM Name	GLM 5 REAP 50pct FP8
Repository 🤗	https://huggingface.co/0xSero/GLM-5-REAP-50pct-FP8
Base Model(s)	GLM 5 zai-org/GLM-5
Model Size	381.5b
Required VRAM	223.3 GB
Updated	2026-03-28
Maintainer	0xSero
Model Type	glm_moe_dsa
Model Files	49.8 GB: 1-of-17 47.2 GB: 2-of-17 43.6 GB: 3-of-17 47.2 GB: 4-of-17 43.6 GB: 5-of-17 47.2 GB: 6-of-17 43.6 GB: 7-of-17 47.2 GB: 8-of-17 43.6 GB: 9-of-17 47.2 GB: 10-of-17 43.6 GB: 11-of-17 47.2 GB: 12-of-17 43.6 GB: 13-of-17 47.2 GB: 14-of-17 43.6 GB: 15-of-17 47.2 GB: 16-of-17 30.3 GB: 17-of-17
Model Architecture	GlmMoeDsaForCausalLM
License	apache-2.0
Context Length	202752
Model Max Length	202752
Transformers Version	5.3.0
Vocabulary Size	154880

Rank the GLM 5 REAP 50pct FP8 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 REAP 50pct FP8

Best Alternatives	Context / RAM	Downloads	Likes
GLM 5.1 NVFP4	198K / 429.9 GB	117353	39
GLM 5 REAP 381B	198K / 762.9 GB	369	3
GLM 5 381B	198K / 762.9 GB	27	3

Note: green Score (e.g. "73.2") means that the model is better than 0xSero/GLM-5-REAP-50pct-FP8.