Arxiv:2305.18290 Base model:quantized:stability... Base model:stabilityai/stablel... Conversational Dataset:huggingfaceh4/ultracha... Dataset:huggingfaceh4/ultrafee... Dataset:intel/orca dpo pairs Dataset:meta-math/metamathqa Dataset:wizardlm/wizardlm evol... En Gguf Instruct Quantized Region:us Stablelm
Model Card on HF 🤗: https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF
Stablelm Zephyr 3B 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)
Stablelm Zephyr 3B GGUF Parameters and Internals
| LLM Name | Stablelm Zephyr 3B GGUF |
| Repository 🤗 | https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF |
| Model Name | StableLM Zephyr 3B |
| Model Creator | Stability AI |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 1.2 GB |
| Updated | 2025-08-04 |
| Maintainer | TheBloke |
| Model Type | stablelm |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | AutoModel |
| License | other |
Best Alternatives to Stablelm Zephyr 3B GGUF
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama32 3B En Emo V3 | 128K / 2 GB | 9 | 0 |
| Llama 3.2 3B VanRossum | 0K / 6.5 GB | 61 | 0 |
| Legal Llama3 Lora Model | 0K / 3.4 GB | 18 | 0 |
| MedQwen3B Reasoner | 0K / 6.2 GB | 134 | 13 |
| ...a Song Stream 3B Instruct GGUF | 0K / 2 GB | 114 | 6 |
| QwQ LCoT 3B Instruct GGUF | 0K / 1.9 GB | 46 | 7 |
| ... Sentient 3.2 3B Instruct GGUF | 0K / 2 GB | 103 | 8 |
| ...ma Doctor 3.2 3B Instruct GGUF | 0K / 2 GB | 105 | 7 |
| ...ma Magpie 3.2 3B Instruct GGUF | 0K / 2 GB | 37 | 2 |
| Llama 3.2 3B Instruct GGUF | 0K / 2 GB | 58 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/stablelm-zephyr-3b-GGUF .
Rank the Stablelm Zephyr 3B 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? 50392 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124