Back to Quant Hub

StarCoder2 15B

15B

BigCode

BigCode's open code model trained on 600+ languages. Great for polyglot dev.

Consumer GPU

16K

Max Context

2

Quant Variants

GGUF Q4_K_M

Best Quality

96.8%

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Format	Level	BPW	VRAM	PPL Loss	Speed	Actions
GGUF	Q4_K_M	4.85	10.5 GB	3.2%	92 tok/s	Calc HF
GPTQ	INT4	4	9.2 GB	4.8%	115 tok/s	Calc HF