Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium Bnb 4bit Smashed is an open-source language model by PrunaAI. Features: 7.4b LLM, VRAM: 8.4GB, Context: 4K, Quantized, LLM Explorer Score: 0.13.
| Additional Notes |
| ||||||
| Training Details |
|
| LLM Name | Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium Bnb 4bit Smashed |
| Repository 🤗 | https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.9.2-Phi-3-Medium-bnb-4bit-smashed |
| Base Model(s) | |
| Model Size | 7.4b |
| Required VRAM | 8.4 GB |
| Updated | 2025-09-23 |
| Maintainer | PrunaAI |
| Model Type | mistral |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Tamtanai | 32K / 14.8 GB | 10 | 0 |
| Mistral Ko Inst Dev | 32K / 14.8 GB | 8 | 4 |