Model
Model explorer

StarCoder2 15B

OPEN
BigCode · StarCoder2 family · released Feb 28, 2024

Flagship 2nd-gen BigCode model, NVIDIA-trained on The Stack v2 (600+ languages, 4T+ tokens); HF/ServiceNow/NVIDIA collaboration.

ReasoningCodingVisionFunction callingTool useAgentic
416.5
Elo · rank #328
Parameters
15B
Active params
15B (dense)
Context
16K tokens
Architecture
Transformer decoder, grouped-query + sliding-window attention (4K window/16K ctx), FIM; NVIDIA-trained
License
BigCode OpenRAIL-M
Languages
600+
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
DS-1000Coding33.8%#1
best: this model · 33.8%
GSM8KMath65.1%#107
best: Llama 3.1 405B · 96.8%
HumanEval+Coding37.8%#33
best: Mistral Small 3.2 (24B) · 92.9%
HumanEvalCoding46.3%#128
best: Claude Opus 4.5 · 99.4%
MBPP+Coding53.1%#34
best: Llama 3.1 405B · 88.6%
MBPPCoding66.2%#45
best: Llama-3.3-Nemotron-Super-49B v1 (Reasoning On) · 91.3%
RepoBenchCoding39.8%#3
best: DeepSeek Coder 33B · 41.9%
Run it locally
VRAM @ Q4
9.4 GB
VRAM @ FP16
30.4 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF
StarCoder2 family
Elo progression across releases
StarCoder2 15BFeb 2024416.5StarCoder2 3BFeb 2024153.0
Resources
HFbigcode/starcoder2-15bGHbigcode-project/starcoder2DOCSbigcode-project.org/docs/about/models
API price weights · each benchmark row carries its own source badge (see methodology)