LLM EXPLORER 59,420 MODELS INDEXED

Phoenix GPTQ by DRXD1000

By DRXD1000 · 12 downloads
HF Repo ↗ Copy URL

Phoenix GPTQ is an open-source language model by DRXD1000. Features: 7.2b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.1.

  Arxiv:2401.10580   4-bit   4bit   Alignment-handbook   Conversational   De   Dpo   Endpoints compatible   Gptq   Mistral   Quantization   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/DRXD1000/Phoenix-GPTQ 

Phoenix GPTQ Parameters and Internals

Model Type 
GPT-like 7B model DPO fine-tuned
Additional Notes 
Model trained in German with GPTQ quantization.
Supported Languages 
German (NLP)
Training Details 
Data Sources:
HuggingFaceH4/ultrachat_200k, argilla/ultrafeedback-binarized-preferences
Hardware Used:
8 x A100 80GB
Input Output 
Input Format:
<|system|> ~~ <|user|> {prompt}~~ <|assistant|>
Accepted Modalities:
text
LLM NamePhoenix GPTQ
Repository 🤗https://huggingface.co/DRXD1000/Phoenix-GPTQ 
Model Size7.2b
Required VRAM4.2 GB
Updated2026-08-25
MaintainerDRXD1000
Model Typemistral
Model Files  4.2 GB
Supported Languagesde
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Phoenix GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Multi Verse Model GPTQ32K / 4.2 GB1111
Garrulus GPTQ32K / 4.2 GB283
HamSter 0.1 GPTQ32K / 4.2 GB72
Mistral Ft Optimized 1227 GPTQ32K / 4.2 GB192
...hat 3.5 1210 Seraph Slerp GPTQ32K / 4.2 GB102
...h Openchat 3.5 1210 Slerp GPTQ32K / 4.2 GB61
Metis 0.5 GPTQ32K / 4.2 GB61
XDAN L1 Chat RL V1 GPTQ32K / 4.2 GB153
Apricot Wildflower 20 GPTQ32K / 4.2 GB121
SAM GPTQ32K / 4.2 GB190
Note: green Score (e.g. "73.2") means that the model is better than DRXD1000/Phoenix-GPTQ.