GLM 4.7 Flash FP8 Dynamic is an open-source language model by unsloth. Features: 30b LLM, VRAM: 32.5GB, Context: 198K, License: mit, MoE.
Arxiv:2508.06471 Base model:quantized:zai-org/g... Base model:zai-org/glm-4.7-fla... Compressed-tensors Conversational En Endpoints compatible Glm4 moe lite Moe Region:us Safetensors Unsloth Zh
Model Card on HF 🤗: https://huggingface.co/unsloth/GLM-4.7-Flash-FP8-Dynamic
GLM 4.7 Flash FP8 Dynamic Parameters and Internals
| LLM Name | GLM 4.7 Flash FP8 Dynamic |
| Repository 🤗 | https://huggingface.co/unsloth/GLM-4.7-Flash-FP8-Dynamic |
| Base Model(s) | |
| Model Size | 30b |
| Required VRAM | 32.5 GB |
| Updated | 2026-03-27 |
| Maintainer | unsloth |
| Model Type | glm4_moe_lite |
| Model Files | |
| Supported Languages | en zh |
| Model Architecture | Glm4MoeLiteForCausalLM |
| License | mit |
| Context Length | 202752 |
| Model Max Length | 202752 |
| Transformers Version | 5.0.0rc3 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | [MASK] |
| Vocabulary Size | 154880 |
Rank the GLM 4.7 Flash FP8 Dynamic 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? 51648 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 v20260327b