Starcoder 15B 4bit is an open-source language model by smallcloudai. Features: 15b LLM, License: openrail, Quantized, Code Generating, LLM Explorer Score: 0.07.
Model Card on HF 🤗: https://huggingface.co/refactai/starcoder_15b_4bit
Starcoder 15b 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)
Starcoder 15B 4bit Parameters and Internals
| LLM Name | Starcoder 15b 4bit |
| Repository 🤗 | https://huggingface.co/refactai/starcoder_15b_4bit |
| Model Size | 15b |
| Updated | 2026-04-01 |
| Maintainer | smallcloudai |
| Model Type | gpt_bigcode |
| Quantization Type | 4bit |
| Generates Code | Yes |
| Model Architecture | GPTBigCodeForCausalLM |
| License | openrail |
| Transformers Version | 4.28.1 |
| Vocabulary Size | 49152 |
| Torch Data Type | float32 |
| Activation Function | gelu |
Best Alternatives to Starcoder 15B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Minotaur 15B 8bit | 0K / 16.5 GB | 8 | 0 |
| WizardCoder 15B V1.0 8bit | 0K / 16.5 GB | 7 | 1 |
| Starcoder 15b 8bit | 0K / GB | 17 | 4 |
| Starcoder 15b 8bit | 0K / GB | 4 | 4 |
| Starcoder 15b 4bit | 0K / GB | 12 | 2 |
| WizardCoder Guanaco 15B V1.1 | 0K / 31 GB | 840 | 12 |
| WizardCoder Guanaco 15B V1.0 | 0K / 31 GB | 837 | 5 |
| ...ardCoder Guanaco 15B V1.1 GPTQ | 0K / 9.2 GB | 40 | 12 |
| ...ardCoder Guanaco 15B V1.0 GPTQ | 0K / 9.2 GB | 7 | 16 |
| WizardCoder 15B V1.0 | 0K / 31 GB | 526 | 763 |
Note: green Score (e.g. "73.2") means that the model is better than refactai/starcoder_15b_4bit .
Rank the Starcoder 15B 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? 52473 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a