| LLM Name | HelpingAI 15B |
| Repository ๐ค | https://huggingface.co/HelpingAI/HelpingAI-15B |
| Model Size | 15b |
| Required VRAM | 31.6 GB |
| Updated | 2025-09-29 |
| Maintainer | HelpingAI |
| Model Type | mixtral |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf|q4_k |
| Model Architecture | MixtralForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.43.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|startoftext|> |
| Vocabulary Size | 64000 |
| Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| HelpingAI 15B | 4K / 31.6 GB | 57 | 12 |
| Helion 4x34B GPTQ | 195K / 58.3 GB | 14 | 3 |
| Shqiponja 15B V1 | 32K / 31.3 GB | 0 | 3 |
| Shqiponja 15B V2 8bit | 32K / 16.3 GB | 5 | 1 |
๐ 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! ๐