Qwen2 0.5B Instruct 4bit 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)
Qwen2 0.5B Instruct 4bit Parameters and Internals
| LLM Name | Qwen2 0.5B Instruct 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Qwen2-0.5B-Instruct-4bit |
| Base Model(s) | |
| Model Size | 0.5b |
| Required VRAM | 0.3 GB |
| Updated | 2024-09-07 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2 0.5B Instruct 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 0.5B Instruct Bnb 4bit | 32K / 0.5 GB | 15063 | 3 |
| ....5B Instruct Bnb 4bit MAC Lora | 32K / 0.5 GB | 6 | 1 |
| New16b3e | 32K / 1 GB | 6 | 0 |
| Newqwen1e | 32K / 1 GB | 5 | 0 |
| Qwen2 0.5B Instruct Sorah | 32K / 1 GB | 5 | 0 |
| New16b3e | 32K / 1 GB | 0 | 0 |
| Newqwen1e | 32K / 1 GB | 0 | 0 |
| Qwen2 0.5B Abyme Merge3 | 128K / 1.3 GB | 20 | 0 |
| Qwen2 0.5B Abyme Merge2 | 128K / 0.3 GB | 9 | 0 |
| Qwen2 0.5B Instruct | 32K / 1 GB | 221507 | 143 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2-0.5B-Instruct-4bit .
Rank the Qwen2 0.5B Instruct 4bit 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803