---

base_model: bigcode/starcoder2-7b inference: false license: bigcode-openrail-m library_name: transformers model_creator: bigcode model_name: StarCoder2 7B pipeline_tag: text-generation quantized_by: Second State Inc. tags:

• code

---

---

StarCoder2-7B-GGUF

Original Model

bigcode/starcoder2-7b

Run with LlamaEdge

• LlamaEdge version: coming soon
• Context size: 4608

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
starcoder2-7b-Q2K.gguf	Q2K	2	2.72 GB	smallest, significant quality loss - not recommended for most purposes
starcoder2-7b-Q3KL.gguf	Q3K_L	3	3.99 GB	small, substantial quality loss
starcoder2-7b-Q3KM.gguf	Q3K_M	3	3.59 GB	very small, high quality loss
starcoder2-7b-Q3KS.gguf	Q3K_S	3	3.09 GB	very small, high quality loss
starcoder2-7b-Q40.gguf	Q40	4	4.04 GB	legacy; small, very high quality loss - prefer using Q3KM
starcoder2-7b-Q4KM.gguf	Q4K_M	4	4.4 GB	medium, balanced quality - recommended
starcoder2-7b-Q4KS.gguf	Q4K_S	4	4.13 GB	small, greater quality loss
starcoder2-7b-Q50.gguf	Q50	5	4.94 GB	legacy; medium, balanced quality - prefer using Q4KM
starcoder2-7b-Q5KM.gguf	Q5K_M	5	5.12 GB	large, very low quality loss - recommended
starcoder2-7b-Q5KS.gguf	Q5K_S	5	4.94 GB	large, low quality loss - recommended
starcoder2-7b-Q6K.gguf	Q6K	6	5.89 GB	very large, extremely low quality loss
starcoder2-7b-Q80.gguf	Q80	8	7.63 GB	very large, extremely low quality loss - not recommended

Quantized with llama.cpp b2308