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

CodeMate V0.1 6.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  CodeMate V0.1 6.0bpw H6 EXL2   URL Share it on

  7   

CodeMate V0.1 6.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: LLM, VRAM: 25.7GB, Context: 16K, License: llama2, Quantized, LLM Explorer Score: 0.12.

  Code   Codemate   En   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/CodeMate-v0.1-6.0bpw-h6-exl2 

CodeMate V0.1 6.0bpw H6 EXL2 Benchmarks

LLME Score: 0.11662
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeMate V0.1 6.0bpw H6 EXL2 (LoneStriker/CodeMate-v0.1-6.0bpw-h6-exl2)
🌟 Advertise your project 🚀

CodeMate V0.1 6.0bpw H6 EXL2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model has undergone very limited testing. Additional safety testing is recommended before real-world deployment.
Supported Languages 
Python (proficient), C/C++ (proficient), TypeScript (proficient), Java (proficient), Additional Languages (proficient)
Training Details 
Data Sources:
Proprietary dataset of high-quality programming problems and solutions
Data Volume:
1.8 billion tokens
Methodology:
Fine-tuned using Flash Attention 2
Context Length:
8096
Training Time:
15 hours
Hardware Used:
40 A100-80GB GPUs
Input Output 
Input Format:
Alpaca/Vicuna instruction format
Accepted Modalities:
text
Output Format:
Generated code solution
Release Notes 
Version:
0.1
Notes:
Initial version of CodeMate
LLM NameCodeMate V0.1 6.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/CodeMate-v0.1-6.0bpw-h6-exl2 
Required VRAM25.7 GB
Updated2025-12-20
MaintainerLoneStriker
Model Typellama
Model Files  8.6 GB: 1-of-4   8.5 GB: 2-of-4   8.4 GB: 3-of-4   0.2 GB: 4-of-4
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to CodeMate V0.1 6.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
... Text Chat 512K 5.0bpw H6 EXL2512K / 4.4 GB21
... Text Chat 512K 6.0bpw H6 EXL2512K / 5.2 GB01
Slimorca Phi 3.5128K / 7.6 GB50
Phi 3.5 Instruct Vul128K / 7.6 GB70
... Text Chat 128K 6.0bpw H6 EXL2128K / 5.2 GB51
Unsloth Phi 4 4bit16K / 8.3 GB9155
QuantumQuill16K / 2.2 GB50
...ocalAI Functioncall Phi 4 V0.316K / 29.4 GB68
PARM V2 Phi 4 4K CoT PyTorch16K / 29.4 GB01
...oros C34b 3.1.2 8.0bpw H6 EXL216K / 34 GB21
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/CodeMate-v0.1-6.0bpw-h6-exl2.

Rank the CodeMate V0.1 6.0bpw H6 EXL2 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? 52721 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