4bit Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-1.5b Code Codegen Codeqwen Conversational En Endpoints compatible Mlx Quantized Qwen Qwen-coder Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen2.5-Coder-1.5B-4bit
Qwen2.5 Coder 1.5B 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)
Qwen2.5 Coder 1.5B 4bit Parameters and Internals
| LLM Name | Qwen2.5 Coder 1.5B 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Qwen2.5-Coder-1.5B-4bit |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 0.9 GB |
| Updated | 2025-03-12 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Generates Code | Yes |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.44.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2.5 Coder 1.5B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Zirel 1.5 | 32K / 3.1 GB | 43 | 0 |
| Text2SQL 1.5B | 32K / 3.1 GB | 22 | 1 |
| FastApply 1.5B V1.0 | 32K / 3.1 GB | 20408 | 22 |
| ...5 Coder 1.5B Instruct Bnb 4bit | 32K / 1.1 GB | 6327 | 1 |
| Qwen2.5 Coder 1.5B Bnb 4bit | 32K / 1.1 GB | 2318 | 2 |
| Qwen Finetune Intermediate | 32K / 3.1 GB | 49 | 0 |
| Replete Coder Qwen2 1.5B | 128K / 3.1 GB | 233 | 23 |
| Qwen2.5 Coder 1.5B Instruct | 32K / 3.1 GB | 50131 | 66 |
| Hammer2.1 1.5B | 32K / 3.1 GB | 5231 | 6 |
| ...n2.5 Coder Draft 1.5B Instruct | 32K / 3.1 GB | 23 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2.5-Coder-1.5B-4bit .
Rank the Qwen2.5 Coder 1.5B 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? 44902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227