DeepAnalyze 8B is an open-source language model by RUC-DataLab. Features: 8b LLM, VRAM: 16.4GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.23.
| LLM Name | DeepAnalyze 8B |
| Repository 🤗 | https://huggingface.co/RUC-DataLab/DeepAnalyze-8B |
| Model Size | 8b |
| Required VRAM | 16.4 GB |
| Updated | 2026-08-25 |
| Maintainer | RUC-DataLab |
| Model Type | qwen3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...epSeek R1 0528 Qwen3 8B Esper3 | 128K / 32.7 GB | 15 | 3 |
| WebWorld 8B | 40K / 16.4 GB | 950 | 64 |
| WebWorld 32B | 40K / 65.8 GB | 342 | 75 |
| WebWorld 14B | 40K / 29.5 GB | 504 | 28 |
| ...nBias Plus SFT Instruct Legacy | 40K / 16.4 GB | 383 | 1 |
| ...n3 8B UnBias Plus SFT Instruct | 40K / 16.4 GB | 54 | 1 |
| QVikhr 3 8B Instruction | 40K / 16.4 GB | 3846 | 10 |
| ATLAS 8B Instruct | 40K / 16.4 GB | 22 | 2 |
| Qwen3 8B ShiningValiant3 | 40K / 32.7 GB | 11 | 3 |
| Qwen3 8B Shadow FT BAAI 2K | 40K / 16.4 GB | 9 | 0 |