Arxiv:2407.10671 Arxiv:2409.12186 4-bit Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-... Chat Code Codegen Codeqwen Conversational En Endpoints compatible Gptq Instruct Quantized Qwen Qwen-coder Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4
Qwen2.5 Coder 1.5B Instruct GPTQ Int4 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 Instruct GPTQ Int4 Parameters and Internals
| LLM Name | Qwen2.5 Coder 1.5B Instruct GPTQ Int4 |
| Repository 🤗 | https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4 |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 1.1 GB |
| Updated | 2025-09-23 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| 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 | float16 |
| Errors | replace |
Best Alternatives to Qwen2.5 Coder 1.5B Instruct GPTQ Int4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... Coder 1.5B Instruct GPTQ Int8 | 32K / 1.8 GB | 1115 | 3 |
| Zirel 1.5 | 32K / 3.1 GB | 18 | 0 |
| Text2SQL 1.5B | 32K / 3.1 GB | 21 | 7 |
| ...5 Coder 1.5B Instruct Bnb 4bit | 32K / 1.1 GB | 2834 | 1 |
| FastApply 1.5B V1.0 | 32K / 3.1 GB | 783 | 38 |
| Replete Coder Qwen2 1.5B | 128K / 3.1 GB | 233 | 23 |
| Qwen2.5 Coder 1.5B Instruct | 32K / 3.1 GB | 166827 | 84 |
| ProseFlow V1.1.5B Instruct | 32K / 3.1 GB | 7 | 1 |
| ...n2.5 Coder Draft 1.5B Instruct | 32K / 3.1 GB | 5 | 0 |
| Arch Agent 1.5B | 32K / 3.1 GB | 130 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4 .
Rank the Qwen2.5 Coder 1.5B Instruct GPTQ Int4 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124