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

BigCodeLlama 92B by nisten

 »  All LLMs  »  nisten  »  BigCodeLlama 92B   URL Share it on

  119   

BigCodeLlama 92B is an open-source language model by nisten. Features: 70b LLM, VRAM: 184GB, Context: 2K, License: mit, Instruction-Based, Code Generating, LLM Explorer Score: 0.14, Arc: 54.8, HellaSwag: 77.8, MMLU: 55.4, GSM8K: 45.

Base model:codellama/codellama... Base model:finetune:codellama/...   Code   Codegen   Conversational   Endpoints compatible   Instruct   Llama   Merge   Mergekit   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nisten/BigCodeLlama-92b 

BigCodeLlama 92B Benchmarks

ARC: 54.78 vs 96.7 (so35)-43.4%
HellaSwag: 77.84 vs 95.3 (gpt4)-18.3%
MMLU: 55.4 vs 88.3 (so35)-37.3%
GSM8K: 44.96 vs 96.4 (so35)-53.4%
LLME Score: 0.13505
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
BigCodeLlama 92B (nisten/BigCodeLlama-92b)
🌟 Advertise your project 🚀

BigCodeLlama 92B Parameters and Internals

Model Type 
conversational
Additional Notes 
This is an experimental 92B parameter model constructed by merging with `../CodeLlama-70b-Python-hf` and `../CodeLlama-70b-Instruct-hf` models using a specific YAML configuration. The model's type is conversational.
LLM NameBigCodeLlama 92B
Repository 🤗https://huggingface.co/nisten/BigCodeLlama-92b 
Base Model(s)  CodeLlama 70B Instruct Hf   codellama/CodeLlama-70b-Instruct-hf
Model Size70b
Required VRAM184 GB
Updated2026-04-26
Maintainernisten
Model Typellama
Instruction-BasedYes
Model Files  9.8 GB: 1-of-19   9.8 GB: 2-of-19   9.6 GB: 3-of-19   9.8 GB: 4-of-19   9.9 GB: 5-of-19   9.7 GB: 6-of-19   10.0 GB: 7-of-19   9.9 GB: 8-of-19   9.6 GB: 9-of-19   10.0 GB: 10-of-19   9.8 GB: 11-of-19   9.9 GB: 12-of-19   9.8 GB: 13-of-19   9.8 GB: 14-of-19   10.0 GB: 15-of-19   9.9 GB: 16-of-19   9.6 GB: 17-of-19   9.7 GB: 18-of-19   7.4 GB: 19-of-19
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to BigCodeLlama 92B

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 70B Instruct Hf4K / 72.3 GB79924
Code Llama 70B Python Instruct4K / 138.1 GB51
CodeLlama 70B Instruct Hf4K / 72.3 GB1306208
CodeLlama 70B Instruct Neuron4K /  GB111
...Llama 70B Instruct Hf 4bit MLX4K / 39.1 GB66425
...70B Instruct Nf4 Fp16 Upscaled4K / 138.7 GB102
...70B Instruct Hf 5.0bpw H6 EXL22K / 43.6 GB66
...70B Instruct Hf 2.4bpw H6 EXL22K / 21.3 GB31
...0B Instruct Hf 2.65bpw H6 EXL22K / 23.4 GB53
...70B Instruct Hf 4.0bpw H6 EXL22K / 35.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than nisten/BigCodeLlama-92b.

Rank the BigCodeLlama 92B 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? 53999 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