4-bit Autotrain compatible Base model:mlabonne/phixtral-4... Base model:quantized:mlabonne/... Code Cognitivecomputations/dolphin-... Conversational Custom code En Gptq Lxuechen/phi-2-dpo Moe Mrm8488/phi-2-coder Phi-msft Quantized Region:us Safetensors Yhyu13/phi-2-sft-dpo-gpt4 en-e...
Model Card on HF 🤗: https://huggingface.co/TheBloke/phixtral-4x2_8-GPTQ
Phixtral 4x2 8 GPTQ Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Phixtral 4x2 8 GPTQ Parameters and Internals
| Model Type |
| ||||||||||||
| Additional Notes |
| ||||||||||||
| Supported Languages |
| ||||||||||||
| Training Details |
| ||||||||||||
| Input Output |
|
| LLM Name | Phixtral 4x2 8 GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/phixtral-4x2_8-GPTQ |
| Model Name | Phixtral 4X2 8 |
| Model Creator | Maxime Labonne |
| Base Model(s) | |
| Model Size | 1.3b |
| Required VRAM | 4.5 GB |
| Updated | 2025-09-17 |
| Maintainer | TheBloke |
| Model Type | phi-msft |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | PhiForCausalLM |
| License | mit |
| Model Max Length | 2048 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
| Activation Function | gelu_new |
Rank the Phixtral 4x2 8 GPTQ 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! 🌟
What open-source LLMs or SLMs are you in search of? 51415 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124