GLM 5.2 FP8 DFlash is an open-source language model by UCloud-org. Features: 3.7b LLM, VRAM: 7.5GB, Context: 1024K, License: mit, LLM Explorer Score: 0.31.
Arxiv:2602.06036 Base model:finetune:zai-org/gl... Base model:zai-org/glm-5.2-fp8 Block-diffusion Custom code Dataset:jessiewei/glm-5.2-fp8-... Dflash Draft-model Endpoints compatible Feature-extraction Glm Qwen3 Region:us Safetensors Speculative-decoding
Model Card on HF 🤗: https://huggingface.co/UCloud-org/GLM-5.2-FP8-DFlash
GLM 5.2 FP8 DFlash Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
GLM 5.2 FP8 DFlash Parameters and Internals
| LLM Name | GLM 5.2 FP8 DFlash |
| Repository 🤗 | https://huggingface.co/UCloud-org/GLM-5.2-FP8-DFlash |
| Base Model(s) | |
| Model Size | 3.7b |
| Required VRAM | 7.5 GB |
| Updated | 2026-07-07 |
| Maintainer | UCloud-org |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | DFlashDraftModel |
| License | mit |
| Context Length | 1048576 |
| Model Max Length | 1048576 |
| Transformers Version | 5.8.1 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 154880 |
Rank the GLM 5.2 FP8 DFlash Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 54868 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a