LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

QVikhr 2.5 1.5B Instruct SMPO MLX 8bit by Vikhrmodels

 »  All LLMs  »  Vikhrmodels  »  QVikhr 2.5 1.5B Instruct SMPO MLX 8bit   URL Share it on

  6   

QVikhr 2.5 1.5B Instruct SMPO MLX 8bit is an open-source language model by Vikhrmodels. Features: 1.5b LLM, VRAM: 1.6GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.18.

  8-bit   8bit Base model:quantized:vikhrmode... Base model:vikhrmodels/qvikhr-...   Conversational   En   Endpoints compatible   Instruct   Mlx   Quantized   Qwen2   Region:us   Ru   Safetensors
Model Card on HF 🤗: https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit 

QVikhr 2.5 1.5B Instruct SMPO MLX 8bit Benchmarks

LLME Score: 0.17541
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
QVikhr 2.5 1.5B Instruct SMPO MLX 8bit (Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit)
🌟 Advertise your project 🚀

QVikhr 2.5 1.5B Instruct SMPO MLX 8bit Parameters and Internals

LLM NameQVikhr 2.5 1.5B Instruct SMPO MLX 8bit
Repository 🤗https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit 
Model NameVikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO
Base Model(s)  Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO   Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO
Model Size1.5b
Required VRAM1.6 GB
Updated2026-05-01
MaintainerVikhrmodels
Model Typeqwen2
Instruction-BasedYes
Model Files  1.6 GB
Supported Languagesru en
Quantization Type8bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.47.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151665
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to QVikhr 2.5 1.5B Instruct SMPO MLX 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...5 1.5B Reasoning Warmup Merged32K / 3.1 GB4140
Shlonak Qwen25 Shami V632K / 3.1 GB2690
...n2.5 1.5B Indonesian Sft Pgabl32K / 3.1 GB230
...1.5B Instruct Unsloth Bnb 4bit32K / 1.5 GB805245
Zirel 1.532K / 3.1 GB180
Text2SQL 1.5B32K / 3.1 GB217
Qwen2.5 1.5B Instruct Bnb 4bit32K / 1.1 GB344265
Qwen2.5 1.5B Claude32K / 3.1 GB80
...5 Coder 1.5B Instruct Bnb 4bit32K / 1.1 GB142262
Qwen2.5 1.5B Instruct 4bit32K / 0.9 GB99803
Note: green Score (e.g. "73.2") means that the model is better than Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit.

Rank the QVikhr 2.5 1.5B Instruct SMPO MLX 8bit Capabilities

🆘 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53570 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer