QVikhr 2.5 1.5B Instruct SMPO MLX 4bit is an open-source language model by Vikhrmodels. Features: 1.5b LLM, VRAM: 0.9GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.16.
| LLM Name | QVikhr 2.5 1.5B Instruct SMPO MLX 4bit |
| Repository 🤗 | https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-4bit |
| Model Name | Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 0.9 GB |
| Updated | 2026-05-21 |
| Maintainer | Vikhrmodels |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ru en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151665 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen25 1.5B Alpaca Id Sft | 32K / 3.1 GB | 2038 | 0 |
| Qwen2.5 1.5B Instruct Legal Id | 32K / 3.1 GB | 1425 | 0 |
| Legal Chatbot Qwen2.5 1.5B Id | 32K / 3.1 GB | 250 | 0 |
| Legal Chatbot Llama3 Finetuned | 32K / 3.1 GB | 389 | 0 |
| Legal Chatbot Llama3 Finetuned | 32K / 3.1 GB | 297 | 0 |
| Legal Qwen2.5 1.5B Sft | 32K / 3.1 GB | 1031 | 0 |
| Legal Chatbot Qwen2.5 1.5B Sft | 32K / 3.1 GB | 871 | 0 |
| ....5B Instruct Legal Chatbot Sft | 32K / 3.1 GB | 592 | 0 |
| Qwen2.5 1.5B Legal Sft | 32K / 3.1 GB | 677 | 0 |
| Legal Chatbot Qwen2.5 1.5B Sft | 32K / 3.1 GB | 506 | 0 |