Bbhqwen4 is an open-source language model by sumink. Features: 3.1b LLM, VRAM: 12.3GB, Context: 32K, LLM Explorer Score: 0.18.
| LLM Name | Bbhqwen4 |
| Repository 🤗 | https://huggingface.co/sumink/bbhqwen4 |
| Model Size | 3.1b |
| Required VRAM | 12.3 GB |
| Updated | 2026-07-19 |
| Maintainer | sumink |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba Passthrough 2 | 128K / 6.2 GB | 7 | 0 |
| Augmented 0defe3c8c8c799fb | 32K / 6.2 GB | 43 | 0 |
| OpenCognito R2 | 32K / 6.2 GB | 259 | 0 |
| Augmented 619958b5bf46bea2 | 32K / 6.2 GB | 9 | 0 |
| Legal Qwen India | 32K / 2.2 GB | 7 | 2 |
| TethysAI Vortex Reasoning | 32K / 6.2 GB | 11 | 0 |
| Bbhqwen | 32K / 12.3 GB | 5 | 0 |
| Bbhqwen2 | 32K / 12.3 GB | 5 | 0 |
| Bbhqwen5 | 32K / 12.3 GB | 5 | 0 |
| Bbhqwen3 | 32K / 12.3 GB | 8 | 0 |