Irix 12B Slush by mergekit-community

 »  All LLMs  »  mergekit-community  »  Irix 12B Slush   URL Share it on

Irix 12B Slush is an open-source language model by mergekit-community. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, Merged, LLM Explorer Score: 0.19.

  Merged Model   Base model:crestf411/mn-slush Base model:dreadpoor/irix-12b-...   Conversational   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Irix 12B Slush Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Irix 12B Slush Parameters and Internals

LLM NameIrix 12B Slush
Repository 🤗https://huggingface.co/mergekit-community/Irix-12B_Slush 
Base Model(s)  MN Slush   Irix 12B Model Stock   crestf411/MN-Slush   DreadPoor/Irix-12B-Model_Stock
Merged ModelYes
Model Size12b
Required VRAM24.5 GB
Updated2026-05-12
Maintainermergekit-community
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Model ArchitectureMistralForCausalLM
Context Length1024000
Model Max Length1024000
Transformers Version4.52.4
Tokenizer ClassPreTrainedTokenizer
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Irix 12B Slush

Best Alternatives
Context / RAM
Downloads
Likes
Qliphoth 12B V1.21000K / 24.5 GB542
MN 12B Mag Mell R11000K / 24.5 GB69558238
Qliphoth 12B V11000K / 24.5 GB1411
Qliphoth 12B V1.11000K / 24.5 GB1121
Celestial Queen 12B1000K / 24.5 GB7112
MN 12B LucidFaun RP RU1000K / 24.5 GB1915
Captain Eris BMO Violent 12B1000K / 24.5 GB3052
Tankie DPE 12B SFT V21000K / 24.5 GB4127
Dans SakuraKaze V1.0.0 12B1000K / 24.5 GB4520
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB981222
Note: green Score (e.g. "73.2") means that the model is better than mergekit-community/Irix-12B_Slush.

Rank the Irix 12B Slush 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? 54148 in total.

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