GLM 4.7 Flash 0.82B MTP is an open-source language model by inference-optimization. Features: 821.3m LLM, VRAM: 1.6GB, Context: 198K, License: mit, MoE, LLM Explorer Score: 0.27.
| LLM Name | GLM 4.7 Flash 0.82B MTP |
| Repository 🤗 | https://huggingface.co/inference-optimization/GLM-4.7-Flash-0.82B-MTP |
| Model Size | 821.3m |
| Required VRAM | 1.6 GB |
| Updated | 2026-10-10 |
| Maintainer | inference-optimization |
| Model Type | glm4_moe_lite |
| Model Files | |
| Model Architecture | Glm4MoeLiteForCausalLM |
| License | mit |
| Context Length | 202752 |
| Model Max Length | 202752 |
| Transformers Version | 5.17.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 154880 |