LLM EXPLORER 60,783 MODELS INDEXED

Phind Codellama 34B V2 EXL2 by latimar

By latimar · 8 downloads
HF Repo ↗ Copy URL

Phind Codellama 34B V2 EXL2 is an open-source language model by latimar. Features: 34b LLM, Context: 16K, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.13, Arc: 24.6, HellaSwag: 27.6, MMLU: 25.8, GSM8K: 23.2.

  Codegen   Exl2   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/latimar/Phind-Codellama-34B-v2-exl2 

Phind Codellama 34B V2 EXL2 Parameters and Internals

Model Type 
llama
Additional Notes 
The model has several quantized branches based on different BPW (Bits Per Weight) and h (hidden layers) configurations, ranging from 2.55-h6 to 5.0-h8.
LLM NamePhind Codellama 34B V2 EXL2
Repository 🤗https://huggingface.co/latimar/Phind-Codellama-34B-v2-exl2 
Model NamePhind-Codellama-34B-v2
Model Creatorhttps://huggingface.co/Phind
Base Model(s)  Phind CodeLlama 34B V2   Phind/Phind-CodeLlama-34B-v2
Model Size34b
Updated2026-07-24
Maintainerlatimar
Model Typellama
Quantization Typeexl2
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.33.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Phind Codellama 34B V2 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 34B Instruct Fp1616K / 67.5 GB1317
CodeLlama 34B Instruct Hf 4bit16K / 19.4 GB632
Codellama Extraction16K / 67.6 GB60
CodeLlama 34B Python Fp1616K / 67.5 GB13214
CodeLlama 34B Fp1616K / 67.5 GB254
Codellama 34B Bnb 4bit16K / 18.2 GB384
XwinCoder 34B 4.0bpw H6 EXL216K / 17.4 GB31
...Codellama 34B V2 Megacode EXL216K /  GB310
...gpt 32K Codellama 34B Instruct32K / 67.5 GB562
CodeLlama 34B Instruct Hf16K / 67.5 GB22872304
Note: green Score (e.g. "73.2") means that the model is better than latimar/Phind-Codellama-34B-v2-exl2.