Tiny Aya Global 8bit Mlx by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Tiny Aya Global 8bit Mlx   URL Share it on

Tiny Aya Global 8bit Mlx is an open-source language model by mlx-community. Features: 942m LLM, VRAM: 3.6GB, Context: 488K, License: cc-by-nc-4.0, Quantized, LLM Explorer Score: 0.27.

  8-bit   8bit   Am   Ar Base model:coherelabs/tiny-aya... Base model:quantized:coherelab...   Bg   Bn   Ca   Cohere2   Conversational   Cs   Cy   Da   De   El   En   Es   Et   Eu   Fa   Fi   Fr   Ga   Gl   Gu   Ha   He   Hi   Hr   Hu   Id   Ig   It   Ja   Jv   Km   Ko   Lo   Lt   Lv   Mg   Mlx   Mr   Ms   Mt   My   Ne   Nl   No   Pa   Pl   Pt   Quantized   Region:us   Ro   Ru   Safetensors   Sk   Sl   Sn   Sr   Sv   Sw   Ta   Te   Th   Tl   Tr   Uk   Ur   Vi   Wo   Xh   Yo   Zh   Zu

Tiny Aya Global 8bit Mlx Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tiny Aya Global 8bit Mlx (mlx-community/tiny-aya-global-8bit-mlx)
๐ŸŒŸ Advertise your project ๐Ÿš€

Tiny Aya Global 8bit Mlx Parameters and Internals

LLM NameTiny Aya Global 8bit Mlx
Repository ๐Ÿค—https://huggingface.co/mlx-community/tiny-aya-global-8bit-mlx 
Base Model(s)  CohereLabs/tiny-aya-global   CohereLabs/tiny-aya-global
Model Size942m
Required VRAM3.6 GB
Updated2026-03-27
Maintainermlx-community
Model Typecohere2
Model Files  3.6 GB
Supported Languagesen nl fr it pt ro es cs pl uk ru el de da sv no ca gl cy ga eu hr lv lt sk sl et fi hu sr bg ar fa ur tr mt he hi mr bn gu pa ta te ne tl ms id vi jv km th lo zh my ja ko am ha ig mg sn sw wo xh yo zu
Quantization Type8bit
Model ArchitectureCohere2ForCausalLM
Licensecc-by-nc-4.0
Context Length500000
Model Max Length500000
Transformers Version4.51.3
Tokenizer ClassCohereTokenizer
Padding Token<PAD>
Vocabulary Size262144
Torch Data Typebfloat16
Errorsreplace

Rank the Tiny Aya Global 8bit Mlx Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52052 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260327b