Model Card on HF 🤗: https://huggingface.co/cupkappu/Phi3-mini-4bit-COIG-CQIA-GGUF
Phi3 Mini 4bit COIG CQIA GGUF 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)
Phi3 Mini 4bit COIG CQIA GGUF Parameters and Internals
| LLM Name | Phi3 Mini 4bit COIG CQIA GGUF |
| Repository 🤗 | https://huggingface.co/cupkappu/Phi3-mini-4bit-COIG-CQIA-GGUF |
| Model Size | 8b |
| Required VRAM | 2.3 GB |
| Updated | 2025-06-01 |
| Maintainer | cupkappu |
| Model Type | mistral |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf|4bit |
| Model Architecture | AutoModel |
Best Alternatives to Phi3 Mini 4bit COIG CQIA GGUF
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Meta Llama 3 8B Instruct GGUF | 0K / 2 GB | 244534 | 89 |
| ...ma 3 8B Instruct 32K V0.1 GGUF | 0K / 2 GB | 232999 | 57 |
| Llama 3 8B Instruct 64K GGUF | 0K / 3.2 GB | 230054 | 13 |
| ...B Instruct Bnb 4bit 24 1 100 1 | 0K / 16.1 GB | 24 | 0 |
| CleverBoi Llama 3.1 8B V2 | 0K / 16.1 GB | 35 | 0 |
| ...leverBoi Llama 3.1 8B Instruct | 0K / 0.2 GB | 79 | 1 |
| ... Old English Tutorial FineTune | 0K / 4.9 GB | 6 | 0 |
| Code Llama Bagel 8B | 0K / 16.1 GB | 122 | 1 |
| ...ist 8B EarlyPrototype 0.4 GGUF | 0K / GB | 6156 | 0 |
| Tulu MathLingo 8B GGUF | 0K / 4.9 GB | 34 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than cupkappu/Phi3-mini-4bit-COIG-CQIA-GGUF .
Rank the Phi3 Mini 4bit COIG CQIA GGUF 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227