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

Granite 8B Code Base 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Granite 8B Code Base 8bit   URL Share it on

  7   
  8bit   Autotrain compatible   Code   Dataset:bigcode/starcoderdata Dataset:codeparrot/github-code...   Dataset:math-ai/stackmathqa Dataset:open-web-math/open-web...   Llama   Mlx   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Granite 8B Code Base 8bit Benchmarks

LLME Score: 0.21454
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Granite 8B Code Base 8bit Parameters and Internals

LLM NameGranite 8B Code Base 8bit
Repository 🤗https://huggingface.co/mlx-community/granite-8b-code-base-8bit 
Base Model(s)  Granite 8B Code Base   ibm-granite/granite-8b-code-base
Model Size8b
Required VRAM8.6 GB
Updated2024-09-19
Maintainermlx-community
Model Typellama
Model Files  5.4 GB: 1-of-2   3.2 GB: 2-of-2   4.5 GB
Quantization Type8bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.41.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size49152
Torch Data Typebfloat16
Granite 8B Code Base 8bit (mlx-community/granite-8b-code-base-8bit)

Best Alternatives to Granite 8B Code Base 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB12
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB41
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB82
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB325
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB516
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB13
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB11
...Instruct 262K HQQ 2bit Smashed256K / 4 GB162
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB11
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/granite-8b-code-base-8bit.

Rank the Granite 8B Code Base 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? 36026 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.
Release v2024072803
  Support LLM Explorer