Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen2.5-3B-8bit
Qwen2.5 3B 8bit 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)
Qwen2.5 3B 8bit Parameters and Internals
| LLM Name | Qwen2.5 3B 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Qwen2.5-3B-8bit |
| Model Size | 3b |
| Required VRAM | 3.3 GB |
| Updated | 2025-07-02 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 8bit |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| 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 Qwen2.5 3B 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...5 3B Instruct Unsloth Bnb 4bit | 32K / 2.4 GB | 57193 | 7 |
| TethysAI Base Reasoning | 32K / 6.2 GB | 55 | 0 |
| Kyro N1 3B | 32K / 6.2 GB | 12 | 12 |
| QwQ LCoT 3B Instruct | 32K / 6.2 GB | 160 | 5 |
| Athena 1 3B | 32K / 6.2 GB | 26 | 1 |
| Qwen2.5 3B Reasoner | 32K / 6.2 GB | 8 | 0 |
| Test StealthThinker | 32K / 6.2 GB | 8 | 0 |
| Qwen2.5 3B Unsloth Bnb 4bit | 32K / 2.6 GB | 4663 | 0 |
| ...2.5 Coder 3B Instruct Bnb 4bit | 32K / 2 GB | 6848 | 4 |
| Qwen2.5 3B Instruct Chat Sft | 32K / 6.2 GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2.5-3B-8bit .
Rank the Qwen2.5 3B 8bit 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? 49328 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124